NeurIPS 2025 Papers

Reconstructing dynamic 3D scenes from monocular videos remains a fundamental challenge in 3D vision. While 3D Gaussian Splatting (3DGS) achieves real-time rendering in static settings, extending it to dynamic scenes is challenging due to the difficulty of learning structured and temporally consistent motion representations. This challenge often manifests as three limitations in existing methods: redundant Gaussian updates, insufficient motion supervision, and weak modeling of complex non-rigid deformations. These issues collectively hinder coherent and efficient dynamic reconstruction. To address these limitations, we propose HAIF-GS, a unified framework that enables structured and consistent dynamic modeling through sparse anchor-driven deformation. It first identifies motion-relevant regions via an Anchor Filter to suppress redundant updates in static areas. A self-supervised Induced Flow-Guided Deformation module induces anchor motion using multi-frame feature aggregation, eliminating the need for explicit flow labels. To further handle fine-grained deformations, a Hierarchical Anchor Propagation mechanism increases anchor resolution based on motion complexity and propagates multi-level transformations. Extensive experiments on synthetic and real-world benchmarks validate that HAIF-GS significantly outperforms prior dynamic 3DGS methods in rendering quality, temporal coherence, and reconstruction efficiency.

Fluorescence microscopy, while being a key driver for progress in the life sciences, is also subject to technical limitations. To overcome them, computational multiplexing techniques have recently been proposed, which allow multiple cellular structures to be captured in a single image and later be unmixed. Existing image decomposition methods are trained on a set of superimposed input images and the respective unmixed target images. It is critical to note that the relative strength (mixing ratio) of the superimposed images for a given input is a priori unknown. However, existing methods are trained on a fixed intensity ratio of superimposed inputs, making them not cognizant of the range of relative intensities that can occur in fluorescence microscopy. In this work, we propose a novel method called scSplit that is cognizant of the severity of the above-mentioned mixing ratio. Our idea is based on InDI, a popular iterative method for image restoration, and an ideal starting point to embrace the unknown mixing ratio in any given input. We introduce (i) a suitably trained regressor network that predicts the degradation level (mixing asymmetry) of a given input image and (ii) a degradation-specific normalization module, enabling degradation-aware inference across all mixing ratios. We show that this method solves two relevant tasks in fluorescence microscopy, namely image splitting and bleedthrough removal, and empirically demonstrate the applicability of scSplit on 5 public datasets. The source code with pre-trained models is hosted at https://github.com/juglab/scSplit/.

Real-world objects are composed of distinctive, object-specific parts. Identifying these parts is key to performing fine-grained, compositional reasoning—yet, large multimodal models (LMMs) struggle to perform this seemingly straightforward task. In this work, we introduce PARTONOMY, an LMM benchmark designed for pixel-level part grounding. We construct PARTONOMY from existing part datasets and our own rigorously annotated set of images, encompassing 862 parts and 5346 objects for evaluation. Unlike existing datasets that simply ask models to identify generic parts, PARTONOMY utilizes highly technical concepts and challenges models to compare objects’ parts, consider part-whole relationships, and justify textual predictions with visual segmentations. Our experiments demonstrate significant limitations in state-of-the-art LMMs (e.g., LISA-13B achieves only 5.9% gIoU), highlighting a critical gap in their part grounding abilities. We note that existing segmentation-enabled LMMs (segmenting LMMs) have two key architectural shortcomings: they use special [SEG] tokens not seen during pretraining which induce distribution shift, and they discard predicted segmentations instead of using past predictions to guide future ones. To address these deficiencies, we train several part-centric LMMs and propose PLUM, a novel segmenting LMM that utilizes span tagging instead of segmentation tokens and that conditions on prior predictions in a feedback loop. We find that pretrained PLUM dominates existing segmenting LMMs on reasoning segmentation, VQA, and visual hallucination benchmarks. In addition, PLUM finetuned on our proposed Explanatory Part Segmentation task is competitive with segmenting LMMs trained on significantly more segmentation data. Our work opens up new avenues towards enabling fine-grained, grounded visual understanding in LMMs.

In the field of computer vision, the task of stereo image super-resolution (StereoSR) has garnered significant attention due to its potential applications in augmented reality, virtual reality, and autonomous driving. Traditional Transformer-based models, while powerful, often suffer from attention noise, leading to suboptimal reconstruction issues in super-resolved images. This paper introduces DIFFSSR, a novel neural network architecture designed to address these challenges. We introduce the Diff Cross Attention Block (DCAB) and the Sliding Stereo Cross-Attention Module (SSCAM) to enhance feature integration and mitigate the impact of attention noise. The DCAB differentiates between relevant and irrelevant context, amplifying attention to important features and canceling out noise. The SSCAM, with its sliding window mechanism and disparity-based attention, adapts to local variations in stereo images, preserving details, and addressing the performance degradation due to misalignment of horizontal epipolar lines in stereo images. Extensive experiments on benchmark datasets demonstrate that DIFFSSR outperforms state-of-the-art methods, including NAFSSR and SwinFIRSSR, in terms of both quantitative metrics and visual quality.

Pre-training techniques have greatly advanced computer vision, with CroCo’s cross-view completion approach yielding impressive results in tasks like 3D reconstruction and pose regression. However, cross-view completion is ill-posed in non-covisible regions, limiting its effectiveness. We introduce Alligat0R, a novel pre-training approach that replaces cross-view learning with a covisibility segmentation task. Our method predicts whether each pixel in one image is covisible in the second image, occluded, or outside the field of view, making the pre-training effective in both covisible and non-covisible regions, and provides interpretable predictions. To support this, we present Cub3, a large-scale dataset with 5M image pairs and dense covisibility annotations derived from the nuScenes and ScanNet datasets. Cub3 includes diverse scenarios with varying degrees of overlap. The experiments show that our novel pre-training method Alligat0R significantly outperforms CroCo in relative pose regression. Alligat0R and Cub3 will be made publicly available.

Event cameras are neuromorphic vision sensors that asynchronously capture pixel-level intensity changes with high temporal resolution and dynamic range. These make them well suited for monocular depth estimation under challenging lighting conditions. However, progress in event-based monocular depth estimation remains constrained by the quality of supervision: LiDAR-based depth labels are inherently sparse, spatially incomplete, and prone to artifacts. Consequently, these signals are suboptimal for learning dense depth from sparse events. To address this problem, we propose Distil-E2D, a framework that distills depth priors from the image domain into the event domain by generating dense synthetic pseudolabels from co-recorded APS or RGB frames using foundational depth models. These pseudolabels complement sparse LiDAR depths with dense semantically rich supervision informed by large-scale image-depth datasets. To reconcile discrepancies between synthetic and real depths, we introduce a Confidence-Guided Calibrated Depth Loss that learns nonlinear depth alignment and adaptively weights supervision by alignment confidence. Additionally, our architecture integrates past predictions via a Context Transformer and employs a Dual-Decoder Training scheme that enhances encoder representations by jointly learning metric and relative depth abstractions. Experiments on benchmark datasets show that Distil-E2D achieves state-of-the-art performance in event-based monocular depth estimation across both event-only and event+APS settings.

We engage in the relatively underexplored task named thermal infrared image enhancement. Existing infrared image enhancement methods primarily focus on tackling individual degradations, such as noise, contrast, and blurring, making it difficult to handle coupled degradations. Meanwhile, all-in-one enhancement methods, commonly applied to RGB sensors, often demonstrate limited effectiveness due to the significant differences in imaging models. In sight of this, we first revisit the imaging mechanism and introduce a Recurrent Prompt Fusion Network (RPFN). Specifically, the RPFN initially establishes prompt pairs based on the thermal imaging process. For each type of degradation, we fuse the corresponding prompt pairs to modulate the model's features, providing adaptive guidance that enables the model to better address specific degradations under single or multiple conditions.In addition, a selective recurrent training mechanism is introduced to gradually refine the model's handling of composite cases to align the enhancement process, which not only allows the model to remove camera noise and retain key structural details, but also enhancing the overall contrast of the thermal image. Furthermore, we introduce the most comprehensive high-quality infrared benchmark covering a wide range of scenarios. Extensive experiments substantiate that our approach not only delivers promising visual results under specific degradation but also significantly improves performance on complex degradation scenes, achieving a notable 8.76% improvement.

Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), yet its application to vision-language models (VLMs) remains underexplored, with existing methods achieving only modest speedups ($<1.5\times$). This gap is increasingly significant as multimodal capabilities become central to large-scale models. We hypothesize that large VLMs can effectively filter redundant image information layer by layer without compromising textual comprehension, whereas smaller draft models struggle to do so. To address this, we introduce Vision-Aware Speculative Decoding (ViSpec), a novel framework tailored for VLMs. ViSpec employs a lightweight vision adaptor module to compress image tokens into a compact representation, which is seamlessly integrated into the draft model's attention mechanism while preserving original image positional information. Additionally, we extract a global feature vector for each input image and augment all subsequent text tokens with this feature to enhance multimodal coherence. To overcome the scarcity of multimodal datasets with long assistant responses, we curate a specialized training dataset by repurposing existing datasets and generating extended outputs using the target VLM with modified prompts. Our training strategy mitigates the risk of the draft model exploiting direct access to the target model's hidden states, which could otherwise lead to shortcut learning when training solely on target model outputs. Extensive experiments validate ViSpec, achieving, to our knowledge, the first substantial speedup in VLM speculative decoding.

Previous methods for image geo-localization have typically treated the task as either classification or retrieval, often relying on black-box decisions that lack interpretability. The rise of large vision-language models (LVLMs) has enabled a rethinking of geo-localization as a reasoning-driven task grounded in visual cues. However, two major challenges persist. On the data side, existing reasoning-focused datasets are primarily based on street-view imagery, offering limited scene diversity and constrained viewpoints. On the modeling side, current approaches predominantly rely on supervised fine-tuning, which yields only marginal improvements in reasoning capabilities. To address these challenges, we propose a novel pipeline that constructs a reasoning-oriented geo-localization dataset, $\textit{MP16-Reason}$, using diverse social media images. We introduce $\textit{GLOBE}$, $\textbf{G}$roup-relative policy optimization for $\textbf{L}$ocalizability assessment and $\textbf{O}$ptimized visual-cue reasoning, yielding $\textbf{B}$i-objective geo-$\textbf{E}$nhancement for the VLM in recognition and reasoning. $\textit{GLOBE}$ incorporates task-specific rewards that jointly enhance localizability assessment, visual-cue reasoning, and geolocation accuracy. Both qualitative and quantitative results demonstrate that $\textit{GLOBE}$ outperforms state-of-the-art open-source LVLMs on geo-localization tasks, particularly in diverse visual scenes, while also generating more insightful and interpretable reasoning trajectories. The data and code are available at https://github.com/lingli1996/GLOBE.

Vision-Language Navigation is a critical task for developing embodied agents that can follow natural language instructions to navigate in complex real-world environments. Recent advances by finetuning large pretrained models have significantly improved generalization and instruction grounding compared to traditional approaches. However, the role of reasoning strategies in navigation—an action-centric, long-horizon task—remains underexplored, despite Chain-of-Thought reasoning's demonstrated success in static tasks like question answering and visual reasoning. To address this gap, we conduct the first systematic evaluation of reasoning strategies for VLN, including No-Think (direct action prediction), Pre-Think (reason before action), and Post-Think (reason after action). Surprisingly, our findings reveal the Inference-time Reasoning Collaps issue, where inference-time reasoning degrades navigation accuracy, highlighting the challenges of integrating reasoning into VLN. Based on this insight, we propose Aux-Think, a framework that trains models to internalize structured reasoning patterns through CoT supervision during training, while preserving No-Think inference for efficient action prediction. To support this framework, we release R2R-CoT-320k, a large-scale Chain-of-Thought annotated dataset. Empirically, Aux-Think significantly reduces training effort without compromising performance.

Estimating agent pose and 3D scene structure from multi-camera rigs is a central task in embodied AI applications such as autonomous driving. Recent learned approaches such as DUSt3R have shown impressive performance in multiview settings. However, these models treat images as unstructured collections, limiting effectiveness in scenarios where frames are captured from synchronized rigs with known or inferable structure. To this end, we introduce Rig3R, a generalization of prior multiview reconstruction models that incorporates rig structure when available, and learns to infer it when not. Rig3R conditions on optional rig metadata including camera ID, time, and rig poses to develop a rig-aware latent space that remains robust to missing information. It jointly predicts pointmaps and two types of raymaps: a pose raymap relative to a global frame, and a rig raymap relative to a rig-centric frame consistent across time. Rig raymaps allow the model to infer rig structure directly from input images when metadata is missing. The global pose raymaps allow the model to reason about the agent’s ego-motion, while the rig raymaps allow the model to infer rig structure directly from input images when metadata is missing. Rig3R achieves state-of-the-art performance in 3D reconstruction, camera pose estimation, and rig discovery -- outperforming both traditional and learned methods by 17-45% mAA across diverse real-world rig datasets, all in a single forward pass without post-processing or iterative refinement.

Monocular 3D tracking aims to capture the long-term motion of pixels in 3D space from a single monocular video and has witnessed rapid progress in recent years. However, we argue that the existing monocular 3D tracking methods still fall short in separating the camera motion from foreground dynamic motion and cannot densely track newly emerging dynamic subjects in the videos. To address these two limitations, we propose TrackingWorld, a novel pipeline for dense 3D tracking of almost all pixels within a world-centric 3D coordinate system. First, we introduce a tracking upsampler that efficiently lifts the arbitrary sparse 2D tracks into dense 2D tracks. Then, to generalize the current tracking methods to newly emerging objects, we apply the upsampler to all frames and reduce the redundancy of 2D tracks by eliminating the tracks in overlapped regions. Finally, we present an efficient optimization-based framework to back-project dense 2D tracks into world-centric 3D trajectories by estimating the camera poses and the 3D coordinates of these 2D tracks. Extensive evaluations on both synthetic and real-world datasets demonstrate that our system achieves accurate and dense 3D tracking in a world-centric coordinate frame.

Recent work has shown that scene text recognition (STR) models are vulnerable to adversarial examples. Different from non-sequential vision tasks, the output sequence of STR models contains rich information. However, existing adversarial attacks against STR models can only lead to a few incorrect characters in the predicted text. These attack results still carry partial information about the original prediction and could be easily corrected by an external dictionary or a language model. Therefore, we propose the Multi-Population Coevolution Search (MPCS) method to attack each character in the image. We first decompose the global optimization objective into sub-objectives to solve the attack pixel concentration problem existing in previous attack methods. While this distributed optimization paradigm brings a new joint perturbation shift problem, we propose a novel coevolution energy function to solve it. Experiments on recent STR models show the superiority of our method. The code is available at \url{https://github.com/Lee-Jingyu/MPCS}.

Mapping the relationship between neural activity and motor behavior is a central aim of sensorimotor neuroscience and neurotechnology. While most progress to this end has relied on restricting complexity, the advent of foundation models instead proposes integrating a breadth of data as an alternate avenue for broadly advancing downstream modeling. We quantify this premise for motor decoding from intracortical microelectrode data, pretraining an autoregressive Transformer on 2000 hours of neural population spiking activity paired with diverse motor covariates from over 30 monkeys and humans. The resulting model is broadly useful, benefiting decoding on 8 downstream decoding tasks and generalizing to a variety of neural distribution shifts. However, we also highlight that scaling autoregressive Transformers seems unlikely to resolve limitations stemming from sensor variability and output stereotypy in neural datasets.

This position paper argues that human pose estimation (HPE) cannot be considered privacy-preserving or human-centric unless privacy is measured and evaluated. Although privacy concerns have become more visible in recent years, HPE systems are still assessed almost exclusively using accuracy metrics. Privacy is neither defined in measurable terms nor linked to regulatory requirements, and common deployment architectures introduce additional risks due to data transmission and storage. We highlight the limitations of current practices, including the continued reliance on RGB inputs and the lack of benchmarks that reflect legal and ethical constraints. We call for a shift in evaluation practices: privacy must become part of how HPE systems are designed, tested, and compared.

3D visual illusion is a perceptual phenomenon where a two-dimensional plane is manipulated to simulate three-dimensional spatial relationships, making a flat artwork or object look three-dimensional in the human visual system. In this paper, we reveal that the machine visual system is also seriously fooled by 3D visual illusions, including monocular and binocular depth estimation. In order to explore and analyze the impact of 3D visual illusion on depth estimation, we collect a large dataset containing almost 3k scenes and 200k images to train and evaluate SOTA monocular and binocular depth estimation methods. We also propose a 3D visual illusion depth estimation framework that uses common sense from the vision language model to adaptively fuse depth from binocular disparity and monocular depth. Experiments show that SOTA monocular, binocular, and multi-view depth estimation approaches are all fooled by various 3D visual illusions, while our method achieves SOTA performance.

Opaque objects reconstructed by 3D Gaussian Splatting (3DGS) often exhibit a falsely transparent surface, leading to inconsistent background and internal patterns under camera motion in interactive viewing. This issue stems from the ill-posed optimization in 3DGS. During training, background and foreground Gaussians are blended via $\alpha$-compositing and optimized solely against the input RGB images using a photometric loss. As this process lacks an explicit constraint on surface opacity, the optimization may incorrectly assign transparency to opaque regions, resulting in view-inconsistent and falsely transparent output. This issue is difficult to detect in standard evaluation settings (i.e., rendering static images), but becomes particularly evident in object-centric reconstructions under interactive viewing. Although other causes of view-inconsistency, such as popping artifacts, have been explored previously, false transparency has not been explicitly identified. To the best of our knowledge, we are the first to quantify, characterize, and develop solutions for this "false transparency" artifact, an under-reported artifact in 3DGS. Our strategy, Noise Guided Splatting (NGS), encourages surface Gaussians to adopt higher opacity by injecting opaque noise Gaussians in the object volume during training, requiring only minimal modifications to the existing splatting process. To quantitatively evaluate false transparency in static renderings, we propose a novel transmittance-based metric that measures the severity of this artifact. In addition, we introduce a customized, high-quality object-centric scan dataset exhibiting pronounced transparency issues, and we augment popular existing datasets (e.g., DTU) with complementary infill noise specifically designed to assess the robustness of 3D reconstruction methods to false transparency. Experiments across multiple datasets show that NGS substantially reduces false transparency while maintaining competitive performance on standard rendering metrics (e.g., PSNR), demonstrating its overall effectiveness.

Skeleton-based hand gesture recognition plays a crucial role in enabling intuitive human–computer interaction. Traditional methods have primarily relied on hand-crafted features—such as distances between joints or positional changes across frames—to alleviate issues from viewpoint variation or body proportion differences. However, these hand-crafted features often fail to capture the full spatio-temporal information in raw skeleton data, exhibit poor interpretability, and depend heavily on dataset-specific preprocessing, limiting generalization. In addition, normalization strategies in traditional methods, which rely on training data, can introduce domain gaps between training and testing environments, further hindering robustness in diverse real-world settings. To overcome these challenges, we exclude traditional hand-crafted features and propose Skeleton Kinematics Extraction Through Coordinated grapH (SKETCH), a novel framework that directly utilizes raw four-dimensional (time, x, y, and z) skeleton sequences and transforms them into intuitive visual graph representations. The proposed framework incorporates a novel learnable Dynamic Range Embedding (DRE) to preserve axis-wise motion magnitudes lost during normalization and visual graph representations, enabling richer and more discriminative feature learning. This approach produces a graph image that richly captures the raw data’s inherent information and provides interpretable visual attention cues. Furthermore, SKETCH applies independent min–max normalization on fixed-length temporal windows in real time, mitigating degradation from absolute coordinate fluctuations caused by varying sensor viewpoints or differences in individual body proportions. Through these designs, our approach becomes inherently topology-agnostic, avoiding fragile dependencies on dataset- or sensor-specific skeleton definitions. By leveraging pre-trained vision backbones, SKETCH achieves efficient convergence and superior recognition accuracy. Experimental results on SHREC’19 and SHREC’22 benchmarks show that it outperforms state-of-the-art methods in both robustness and generalization, establishing a new paradigm for skeleton-based hand gesture recognition. The code is available at https://github.com/capableofanything/SKETCH.

Starting from flow- and diffusion-based transformers, Multi-modal Diffusion Transformers (MM-DiTs) have reshaped text-to-vision generation, gaining acclaim for exceptional visual fidelity. As these models advance, users continually push the boundary with imaginative or rare prompts, which advanced models still falter in generating, since their concepts are often too scarce to leave a strong imprint during pre-training. In this paper, we propose a simple yet effective intervention that surfaces rare semantics inside MM-DiTs without additional training steps, data, denoising-time optimization, or reliance on external modules (e.g., large language models). In particular, the joint-attention mechanism intrinsic to MM-DiT sequentially updates text embeddings alongside image embeddings throughout transformer blocks. We find that by mathematically expanding representational basins around text token embeddings via variance scale-up before the joint-attention blocks, rare semantics clearly emerge in MM-DiT’s outputs. Furthermore, our results generalize effectively across text-to-vision tasks, including text-to-image, text-to-video, and text-driven image editing. Our work invites generative models to reveal the semantics that users intend, once hidden yet ready to surface.