paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

MITE-Net: SWaP-Optimized 4K Video Tiny Target Perception for Embodied Edge SAR

Mingshuo Xu, Mu Hua, Jigen Peng, Qi Wang, Shigang Yue

Real-time tiny target perception in high-resolution imagery is critical for embodied Search-and-Rescue (SAR) missions. However, strict Size, Weight, and Power (SWaP) constraints on edge devices like UAVs create a bottleneck: traditional image downsampling causes severe feature loss, while slice-based processing incurs prohibitive latency. To address this gap, this paper introduces a comprehensive framework encompassing a novel architecture, specialized datasets, and hardware-level benchmarks. First, we propose MITE-Net, a SWaP-optimized cascaded architecture, which couples a bio-inspired, learning-free Tiny Target Motion-Based Region Proposal Network (TTM-RPN) with a sub-0.14M-parameter R-CNN-like head. Second, to standardize 4K tiny target evaluation, we construct the SAR-Tiny Datasets by relabeling two challenging UAV datasets: SeaDroneSee-Tiny (dynamic maritime scenes, tiny targets predominantly of 64-256 pixels ) and UAVID-Tiny (cluttered urban scenes, extremely tiny targets, less than 64 pixels). Third, we benchmark against state-of-the-art YOLO models on an edge device, NVIDIA Jetson AGX Xavier, where MITE-Net directly processes 4K maritime imagery, achieving a 100\% search success rate at 30.33 FPS. Consuming merely 3.19 W (9.51 FPS/W), MITE-Net vastly outperforms YOLO baselines in target recall and energy efficiency. Conversely, UAVID-Tiny evaluations expose a compound structural limitation: the learning-free bionic front-end struggles against urban backgrounds, while the ultra-lightweight head lacks representational capacity for complex features. Ultimately, this work delivers an efficient onboard perception paradigm and a rigorous baseline guiding future end-to-end SAR architectures.

arXiv

FlowDance: Music-Driven Dance Video Generation with Parallel Pose and RGB Streams

Genying Li, Boda Lin, Jiachen Li, Zijian Jia, Haojie Zheng, Yiming Wang, Shuchen Weng, Si Li

Music-driven dance video synthesis aims to animate a reference person according to a given music clip. The task is challenging because it requires a model to jointly learn music-to-motion correspondence, identity-preserving human animation, temporal coherence, and visually realistic video generation. We present FlowDance, a music-driven dance video generation framework that integrates explicit motion modeling with reference-preserving visual synthesis through parallel pose and RGB streams. We further introduce timestep-aware pose injection to adapt structural guidance across denoising steps and persistent identity injection to preserve the reference appearance over long video. To support this task, we further build a popularity-curated, high-resolution in-the-wild dance video dataset with synchronized music, RGB videos, 3D body motion, camera parameters, and projected 2D pose annotations. Extensive experiments show that FlowDance achieves strong performance in both dance motion generation and music-driven dance video synthesis.

arXiv

From Generation to Matching: A Development Report on Personalized Chinese Handwriting

Yiwei Liu

This paper documents a frozen engineering project on personalized Chinese handwriting. The project started from approximately 200 real handwriting images from one user, covering 197 unique Chinese characters, and was initially formulated as few-shot generation of unseen characters. A sequence of canonical-centered personalization routes repeatedly exposed the same conflict: increasing structural pressure made outputs more canonical, while increasing personalization could damage identity-defining strokes. The project was therefore reset around real-human character equivalence classes. A multi-writer CASIA candidate pool showed that a USER-compatible realization often already existed among valid human samples. The task consequently changed from synthesis to character-wise matching, followed by cross-writer composition into a virtual writer. The frozen system uses real-ink features, character-specific human population percentiles, top-20 candidate pruning, and greedy hardest-first whole-row selection. On the covered target set, all 197 USER characters had real-human candidates, and the 100-character evaluation subset was covered 100/100. Knowncharacter held-out comparisons included a row judged visually almost indistinguishable from genuine USER handwriting. A 60- episode stability audit placed every episode in a predefined A-like machine-proxy region, but these were not independent human A-level judgments. The final evidence supports stable practical B-level quality, with many outputs approaching A-level under the USER-defined criterion. The report records why generation became unnecessary for this case without claiming unrestricted or universal handwriting synthesis.

arXiv

PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection

Chengyao Jia, Ruixuan Wang

Out-of-distribution (OOD) detection remains challenging for image classifiers, especially when near-OOD samples lie close to in-distribution (ID) class boundaries. Recent vision-language detectors improve OOD detection through class semantics, local prompting, or LLM-generated outlier concepts, but seldom use language as explicit boundary evidence between confusing ID classes. We propose Pairwise Witness Local Rejection (PWLR), which uses an MLLM offline to describe visible local cues that favor one ID class over a specific rival class. These cue phrases are then screened with ID-only data under a frozen vision-language backbone, so that only reliable local verifiers are kept. At inference, PWLR first retains a small set of globally plausible classes, then checks whether any of them is locally supported against its most relevant rivals, and finally combines this pairwise local evidence with the global class score through calibration. Experiments on ImageNet-100 far-OOD, cleaner/challenging OOD and near-OOD benchmarks show that PWLR consistently improves strong vision-language baselines across multiple backbones. Source code will be released.

arXiv

Emergent 3D Instance Segmentation from Self-Supervised Point Transformers

Ted Lentsch, Santiago Montiel-Marín, Holger Caesar, Julian F. P. Kooij

Unsupervised 3D instance segmentation of outdoor LiDAR scans has traditionally relied on handcrafted geometric priors such as density-based clustering, motion cues, or projected 2D detections. In this work, we investigate whether a frozen, self-supervised point transformer already contains the structural information required to isolate object instances without any handcrafted geometric prior. Using this transformer purely as a feature extractor, we probe its internal representations across the SemanticKITTI, nuScenes, and Waymo Perception datasets. Our analysis yields four core insights: (1) the instance signal concentrates in the attention queries and keys rather than in the values or final output features; (2) output features semantically collapse, merging adjacent same-class objects that the queries and keys keep distinct; (3) this instance signal is bimodal in depth, strongest at the shallowest and deepest encoder stages; and (4) this signal is driven predominantly by the rotary position encoding (RoPE), whose removal collapses its advantage. We put these findings into our method TokenGraph3D, a training-free segmenter that groups points via connected components on a key-similarity graph, using neither density-based clustering nor proximity priors. Under identical prior-free conditions, we substantially outperform output-feature baselines, making the emergent 3D instance structure visible.

arXiv

ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence

Xiaohan Zhang, Feng Gu, Xudong Rao, Xuhao Pan, Tao Wei, Zhou Pan, Kun Zhan

Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-centric approaches typically treat spatial reasoning as independent question-answer instances, enabling shortcut-based answering and providing limited supervision for persistent spatial understanding. To address this, we introduce ChainSpace, a chained-reasoning paradigm that structures spatial reasoning as a state-preserving multi-round process. In this paradigm, spatial questions are organized into logically constrained and jointly consistent chains, where later questions depend on spatial constraints established in earlier rounds. Following this principle, we instantiate ChainSpace-Bench, a manually annotated real-world multi-round benchmark with a Chain-Aware Metric, and ChainSpace-Pipeline, a simulator-based chain-structured supervision generation framework for spatial intelligence training. Experiments show that ChainSpace-Bench exposes chain-level failures that are not captured by isolated question accuracy. Additionally, with a relatively small amount of simulator-generated chained data, models trained by ChainSpace-Pipeline achieve the best performance among open-source models on ChainSpace-Bench and transfer competitively to multiple external spatial intelligence benchmarks. These results establish ChainSpace as an effective paradigm for more faithful evaluation and more data-efficient learning of spatial intelligence.

arXiv

RoofGS: Roofline-Guided End-to-End Acceleration of 3D Gaussian Splatting

Yang Luo, Yan Gong, Yongsheng Gao, Jie Zhao

3D Gaussian Splatting (3DGS) enables real-time novel-view synthesis but remains limited on GPUs at high resolutions. Through a stage-wise Roofline characterization, we identify two distinct hardware bottlenecks: global memory traffic dominates the front end, whereas instruction throughput limits rasterization. Guided by this analysis, we develop RoofGS, a rendering framework that applies bottleneck-specific optimizations rather than generic kernel acceleration. For the memory-bound front end, we design a resolution-adaptive quantized depth sorting key that compresses each key to 32 bits. For the compute-bound rasterizer, we introduce a range-aware bit-level fast exponential approximation tailored to the bounded exponent range after opacity culling, with a derived per-pixel error bound. These two core techniques are complemented by additional optimizations (kernel fusion, compact attribute storage, culling, dual-pixel evaluation) that additionally reduce memory traffic and improve instruction-level parallelism. Experiments show that RoofGS achieves a 10.1$\times$ end-to-end speedup over 3DGS at 4K on an RTX 4090, increasing throughput from 61 to 616 FPS, with only a 0.028 dB PSNR loss.

arXiv

ES3D: Embedding Semantics into 3D Space for Component-Aware Editing

Xuancheng Jin, Rengan Xie, Jiayuan Lu, Wenting Zheng, Rui Wang, Yuchi Huo, Lincheng Li, Yingfeng Chen

Existing 3D editing methods have made notable progress in controllability, yet they remain limited in several important ways. Most approaches rely on text-driven editing, which struggles to express fine-grained visual changes intended by the user. Moreover, many methods require manually supplied 3D masks or introduce unintended changes to regions that should remain untouched. These limitations largely arise from the absence of fine-grained semantic understanding, making it difficult for existing models to retrieve or modify specific 3D components. We introduce ES3D, a framework that embeds semantics directly into 3D space, enabling component-aware retrieval and editing of a 3D asset conditioned on multiple local reference images and optional text queries. We first construct a 3D semantic embedding by projecting multi-view semantic features into the voxelized space of the asset. We then perform 3D component retrieval by computing feature similarity between the 3D semantic embedding and the semantic embeddings of image or text queries. For editing, we employ a pretrained 3D generative model with an inpainting mechanism to modify the retrieved components guided by user-provided images while preserving the rest of the asset. Overall, ES3D is a 3D editing framework that retrieves editable regions based on semantic cues and uses multiple images as conditions. Extensive experiments demonstrate that ES3D produces geometrically consistent and semantically coherent edits, enabling robust image-based and text-assisted control for 3D editing.

arXiv

Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification

Haadia Amjad, Ronald Tetzlaff

Deep Neural Networks (DNNs) deployed in high-risk domains, such as healthcare and autonomous driving, must be not only accurate but also understandable to ensure user trust. In real-world computer vision tasks, these models often operate on complex images containing background noise and are heavily annotated. To make such models explainable, Concept-based Explainable AI (CXAI) methods need to be assessed for their applicability and problem-solving capacity. In this work, we explore CXAI use cases in multi-label classification by training two DNNs, VGG16 and ResNet50, on the 20 most annotated labels in the MS-COCO dataset (Microsoft Common Objects in Context). We apply two CXAI methods, CRP (Concept Relevance Propagation) and CRAFT (Concept Recursive Activation FacTorization), to generate concept-level explanations and investigate the overall evaluations. Our analysis reveals three key findings: (1) CXAI highlights learning weaknesses in DNNs, (2) higher concept distinctiveness reduces label and concept confusion, and (3) environmental concepts expose dataset-induced biases. Our results demonstrate the potential of CXAI to enhance the understanding of model generalizability and to diagnose bias instigated by the dataset.

arXiv

Anatomical and Physical Supervision for CT-less PET Attenuation Correction: BIC-MAC 2026 Challenge

Petros Chatzitoulousis, George K. Matsopoulos

This report describes our submission to the Big Cross-Modal Attenuation Correction (BIC-MAC) 2026 Challenge for CT-less PET attenuation correction through multimodal pseudo-CT synthesis. We build upon a standard nnU-Net architecture and combine anatomical and physical supervision to improve both pseudo-CT quality and downstream PET reconstruction. Anatomical supervision is introduced through a frozen TotalSegmentator feature extractor, anatomy-guided structural constraints and patch sampling, while physical supervision is achieved using a differentiable attenuation correction factor projection loss based on multi-angle attenuation projections. Furthermore, the network is initialized with pretrained weights obtained from training on the SynthRAD Challenge MR-to-CT dataset. Minimal architectural modifications are applied, while performance improvements are pursued across the nnU-Net pipeline, including preprocessing, plans, and supervision design, among other components. Our final submission demonstrates the effectiveness of combining anatomical supervision, attenuation physics, and efficient nnU-Net scaling for CT-less PET attenuation correction.

arXiv

What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA

Jinhwan Seo, Kyubeom Han, Jumin Lee, Junhyug Noh, Sung-Eui Yoon

We study a critical yet overlooked failure mode in Grounded Video Question Answering: question-invariant grounding, where models predict nearly identical temporal segments for different questions about the same video. We trace this behavior to two structural limitations in prior common designs: (i) modality isolation that fixes video representations before they receive question semantics, and (ii) weak question injection inside the grounding module. To address this, we propose GroundFormer, which conditions video features on question intent before localization via learnable communication tokens that mediate directed visuo-lingual interaction. On top of the question-conditioned features, a factorized MIL cross-attention couples answer selection with temporal evidence under candidate-level supervision, while Gaussian smoothing converts peaked attention into temporally coherent segments. We further introduce a hierarchical multi-modal contrastive loss that aligns video, question, and answer embeddings across a two-pass training pipeline. GroundFormer achieves state-of-the-art grounded VideoQA performance on NExT-GQA and STAR, substantially improving question-discriminative temporal grounding.

arXiv

PixelControl: Fine-Grained Condition Fidelity in Text-to-Image Diffusion

Xin Lin, Haodong LI, Zhifei Zhang, Yutong Yang, Haitian Zheng, Juanxi Tian, Zhe Lin, Truong Nguyen

Controllable text-to-image diffusion models can often follow the global layout of spatial conditions, yet still violate fine-grained structures such as object boundaries, thin contours, and medium/small conditioned regions. This limitation is especially problematic for VAE-based latent diffusion, where spatial compression can weaken high-frequency and low-area condition signals. We propose PixelControl, a pixel-space controllable diffusion framework for fine-grained condition fidelity. Built on a PixelDiT-style backbone, PixelControl avoids the latent bottleneck and introduces two complementary designs. First, Structure-Aware Control Injection derives a condition structure map and uses it to strengthen injected control residuals around spatially sensitive regions. Second, Multi-Scale Pyramid Cycle Loss verifies generated images against condition-derived structures across multiple resolutions, balancing global layout consistency with local boundary and detail accuracy. PixelControl supports depth, segmentation, edge, and their combinations through modality-specific control branches with lightweight gated fusion. Experiments across depth, segmentation, and edge control show that PixelControl improves structural fidelity and visual quality over existing controllable generation methods, with especially strong gains on boundaries and medium/small conditioned regions. The project page can be found at: https://linxin0.github.io/pixelcontrol_homepage/pixelcontrol-site/

arXiv

Bitstream Action Recognition is Byte Modeling

Fangcheng Li, Chaoran Huang, Tianyi Liu, Wenyang Liu, Kejun Wu, Qiong Liu, You Yang, Zhengguo Li

Conventional action recognition typically relies on successful pixel decoding of the bitstream. However, bitstream corruption during storage or transmission may cause severe visual artifacts or even decoding failure, posing a significant challenge to reliable action recognition. Bitstream Action Recognition (BAR) aims to overcome the dependency on decoding and the vulnerability to corruption. In this paper, we propose a novel BAR framework, Bitstream Recognition via Anchoring Corrupted Embeddings (BRACE). BRACE is a dual-branch byte-modeling architecture that treats a corrupted bitstream and its intact counterpart as two byte realizations of the same action. This guides the generation of rich and stable representations for robustness to corruption through Intact-Anchored Representation Alignment (IARA). The intact representation serves as a stable anchor, and the corrupted one is aligned to it at the embedding and decision levels under Unreliable-Anchor Suppression (UAS), entirely in representation space and without repairing the bitstream. To address the scarcity of corrupted bitstreams in practice, we introduce the Real-world Bitstream Corruption Simulator (RBCS), a four-parameter simulator that reproduces bit-flip and byte-loss errors arising in transmission and storage. Building on RBCS, we construct the first large-scale BAR dataset (BAR-D), which comprises the BAR-Stanford40 and BAR-PPMI subsets and spans diverse corruption types and severity levels. Finally, we build a large benchmark on BAR-D involving 14 action recognition methods from the pixel, compressed, and bitstream domains. Extensive experiments demonstrate that BRACE has superior robustness to bitstream corruption than all comparison methods. Ablation studies further validate the effectiveness of the proposed RBCS augmentation and IARA.

arXiv

RRFC: Recursive Refinement via Feedback Conditioning for Iterative Image-to-Image Generation

Kareem Hassani, Chaymaa Abbas, Hadi Al Mubasher, Mariette Awad

Conditional image-to-image generators are single-shot: they map input features to an output in one forward pass and treat it as final, with no opportunity to improve on it. Although trained to produce the best possible result in one step, such a model leaves room for improvement if it can adaptively revise its own output over iterations. We propose Recursive Refinement via Feedback Conditioning (RRFC), a novel feedback-conditioning framework for iterative output refinement that teaches a model to adaptively revise its output by conditioning on a new signal, namely its most recent previous prediction, which is fed back as an auxiliary set of channels alongside the original input. This preserves the generator's core architecture while modifying its conditioning interface and, depending on the model family, its training or inference procedure, so RRFC can be attached to existing generators without redesign. We evaluate RRFC across six baselines spanning adversarial, equilibrium, and diffusion-based models and three paired image-to-image translation tasks. Across 18 architecture-task settings, RRFC yields seven Holm-corrected improvements, seven degradations, and four non-significant changes. The gains concentrate on reconstruction-fidelity and identity settings, while five of the seven degradations fall on the single semantic-layout task, where every model declines. These results indicate that feedback-based refinement helps when its objective overlaps with the evaluated property, and that its gains concentrate on the tasks where that overlap holds.

arXiv

Automated Fetal Brain MRI Biometry in Healthy and Pathological Cases

Ema Masterl, Tina Vipotnik Vesnaver, Nejc Šubič, Žiga Špiclin

Automated biometric analysis of fetal brain MRI enables reproducible, observer-independent quantitative assessment, yet existing methods are often restricted to few measurements or evaluated only on healthy cases. We assemble and evaluate an automated biometric analysis pipeline that localizes 22 anatomical landmarks on NeSVoR-reconstructed 3D volumes and derives 11 clinically relevant measurements spanning supratentorial, ventricular, cerebellar, and midline structures. We compare two landmark localization models, H3DE-Net and SCN, on a heterogeneous cohort of 122 acquisitions (both healthy controls and range pathologies). Localization accuracy was assessed with a linear mixed-effects model, agreement with normative growth trajectories with calibrated centile charts, and diagnostic utility with a decision tree classifying VM severity. H3DE-Net achieved significantly lower localization error than SCN across all landmarks (mean 1.36 mm vs. 3.58 mm in HC and 1.90 mm vs. 4.13 mm in PC; p < 0.001), and outperformed a GA-based regression baseline in 7 of 11 measurements. H3DE-Net measurements yielded higher classification AUC in every diagnostic group, with the clearest advantage in separating healthy controls from VM. Decision tree thresholds for ventricular width fell near the clinical 10 mm and 15 mm cut-offs used to define and grade VM.

arXiv

Training-Free Long-Term Multi-Object Tracking for Sports Video Analytics

Tomasz Stanczyk, Seongro Yoon, Francois Bremond

Long-term multi-object tracking in sports remains challenging due to frequent occlusions, rapid camera motion, and repeated player reappearances. We introduce McByte++, a training-free tracking-by-detection framework that integrates lightweight mask propagation, conditional camera motion compensation, and online re-identification within a unified pipeline. Compared to its predecessor, McByte++ substantially improves runtime efficiency while enhancing identity preservation. On SoccerNet-tracking and SportsMOT benchmarks, McByte++ achieves up to +3.0 HOTA and +6.1 IDF1 improvements over the original McByte in the online setting, with further gains when combined with offline global association. Replacing heavy segmentation components and optimizing motion modeling yields up to an order-of-magnitude speed increase. All results are obtained without detector retraining or dataset-specific tuning. Code will be made available at https://github.com/tstanczyk95/McBytePlusPlus.

arXiv

Counterfactual Sensitivity Is Not Repairability: Auditing Replay Probes for Video Evidence

Rama AlHamidi, Rasul Khanbayov, Erchin Serpedin, Hasan Kurban

Tool-using video agents retrieve visual evidence before answering, but the final answer is not forced to depend on what was retrieved. The natural black box test is counterfactual: destroy the semantic content of the frames the agent retrieved and check whether the answer changes, against a matched sham that re-executes the identical pipeline on those same frames. We introduce CARVE, a black-box counterfactual probe that compares answer changes under matched SHAM and DESTROY replays. Across three independent k=3 runs on a frozen VideoExplorer-style agent, DESTROY changes the answer 29.3 percentage points more often than SHAM, yielding a large and reproducible aggregate effect. Question-level scores are less stable, and increasing the replay budget from k=3 to k=10 reduces ties but weakens the original zero-threshold routing policy. At k=3, CARVE selects 538 of 1,258 LVBench questions and improves accuracy by 3.26 points, with higher fallback yield than most matched random subsets. The score shows only a weak association with annotated temporal coverage, so CARVE is best understood as a routing signal rather than a direct grounding classifier. Our implementation is available at https://github.com/KurbanIntelligenceLab/CARVE.

arXiv

BASeg: Boundary-Aware Remote Sensing Segmentation with Structural Penalties

Yuexi Song, Kailai Sun, Zhuoyu Wang, Mingyi He, Paul Pu Liang, Shenhao Wang, Jinhua Zhao

Semantic segmentation is a core computer vision task in the remote sensing field, accelerating advancements in ur- ban development, agriculture, ecology, water resources, and environmental monitoring. However, recent methods usually struggle to capture fine-grained object features and bound- ary details. Besides, current widely used datasets often lack city morphology diversity and segmentation on generative im- ages remains largely unexplored. To address these issues, we propose a Mahalanobis-Angle Boundary Loss (MABL) that explicitly enhances boundary and shape consistency. MABL jointly models structural importance and boundary orientation through Mahalanobis distance-based weighting and angle- aware penalty. It can be readily integrated into diverse seg- mentation architectures and consistently improves their accu- racy. Built upon MABL, we introduce BASeg, a boundary- aware remote sensing segmentation framework with Struc- tural Penalties. BASeg integrates a Global Visual State Space module (GSM) with a Cross-Feature Fusion module (CFM) to capture both long-range contextual dependencies and fine- grained local details. Additionally, we establish a global 10- city benchmark dataset (GCD-25k) to facilitate accurate build- ing and road segmentation. Extensive experiments on four remote-sensing benchmarks demonstrate that BASeg consis- tently outperforms existing methods, achieving up to a 2.8% improvement in mIoU while producing more accurate object boundary segmentation across diverse scenes. Moreover, integrating MABL into multiple existing segmentation archi- tectures consistently improves performance across datasets, demonstrating its robustness and broad applicability.

arXiv

Scalable Black-Box Model Attribution for Images

Asaf Livne, Amir Jevnisek, Shai Avidan

The rapid proliferation of generative models raises the model attribution problem: given only an image, can we determine which model produced it? Existing methods have grown as elaborate as the generators they target, on the as- sumption that a more sophisticated model demands a more sophisticated attributor. We show it does not. RPA (Raw- Patch Attribution) attributes images in the strictest black- box setting with a lightweight CNN. Despite its simplicity, it attributes more models at higher accuracy than prior work, reaching 98.0% on 25-class DRAGON and 92.9% on 27- class OpenFake; it is data-efficient and runs at a cost inde- pendent of the number of candidate models; and it stays ro- bust to the compression, blur, and resizing images undergo in the wild. Training for closed-set attribution yields a ver- satile feature extractor: the same representation recovers model lineage without supervision, flags and groups unseen generators, and admits new models through few-shot adap- tation rather than retraining.

arXiv

Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats

Bin Ren, Qi Ma, Yue Li, Zongyan Han, Yidi Li, Yuqian Fu, Rao Muhammad Anwer, Theo Gevers, Fahad Shahbaz Khan, Salman Khan

3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance. Fixed-budget encoders consume sampled observations of Gaussian assets, so the same object may be observed through different primitive realizations. Existing self-supervised methods mainly reconstruct masked Gaussian attributes, tying supervision to one sampled realization and requiring an input-space decoder. Latent prediction offers an alternative, but its application to Gaussian tokens requires targets that accommodate coupled attributes and heterogeneous spatial support. We introduce Gaussian-JEPA, which predicts representations of held-out Gaussian token blocks from visible context. An online encoder processes the context, while a shared exponential-moving-average encoder supplies stop-gradient features for multi-scale targets. Complementary target projections and feature-space grounding provide latent supervision without reconstructing Gaussian attributes. We evaluate the features under Gaussian resampling, partial observations, and renderable shape completion, together with transfer to part segmentation and object classification. Compared with matched reconstruction pretraining, Gaussian-JEPA is more consistent across resampled inputs, retains more instance information under partial observations, and provides stronger frozen features for Gaussian completion. These results support latent prediction as an effective objective for reusable 3D Gaussian representations. Code is on the project page (https://amazingren.github.io/Gaussian-JEPA/).

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.