ICLR 2025 Papers

Attribution algorithms explain computer vision models by attributing the model response to pixels within the input. Existing attribution methods generate explanations by combining transformations of internal model representations such as class activation maps, gradients, attention, or relevance scores. The effectiveness of an attribution map is measured using attribution quality metrics. This leads us to pose the following question: if attribution methods are assessed using attribution quality metrics, why are the metrics not used to generate the attributions? In response to this question, we propose a Metric-Driven Attribution for explaining Vision Transformers (ViT) called MDA. Guided by attribution quality metrics, the method creates attribution maps by performing patch order and patch magnitude optimization across all patch tokens. The first step orders the patches in terms of importance and the second step assigns the magnitude to each patch while preserving the patch order. Moreover, MDA can provide a smooth trade-off between sparse and dense attributions by modifying the optimization objective. Experimental evaluation demonstrates the proposed MDA method outperforms $7$ existing ViT attribution methods by an average of $12\%$ across $12$ attribution metrics on the ImageNet dataset for the ViT-base $16 \times 16$, ViT-tiny $16 \times 16$, and ViT-base $32 \times 32$ models. Code is publicly available at https://github.com/chasewalker26/MDA-Metric-Driven-Attributions-for-ViT.

While imitation learning (IL) offers a promising framework for teaching robots various behaviors, learning complex tasks remains challenging. Existing IL policies struggle to generalize effectively across visual and spatial variations even for simple tasks. In this work, we introduce **SPHINX**: **S**alient **P**oint-based **H**ybrid **I**mitatio**N** and e**X**ecution, a flexible IL policy that leverages multimodal observations (point clouds and wrist images), along with a hybrid action space of low-frequency, sparse waypoints and high-frequency, dense end effector movements. Given 3D point cloud observations, SPHINX learns to infer task-relevant points within a point cloud, or *salient points*, which support spatial generalization by focusing on semantically meaningful features. These salient points serve as anchor points to predict waypoints for long-range movement, such as reaching target poses in free-space. Once near a salient point, SPHINX learns to switch to predicting dense end-effector movements given close-up wrist images for precise phases of a task. By exploiting the strengths of different input modalities and action representations for different manipulation phases, SPHINX tackles complex tasks in a sample-efficient, generalizable manner. Our method achieves **86.7%** success across 4 real-world and 2 simulated tasks, outperforming the next best state-of-the-art IL baseline by **41.1%** on average across **440** real world trials. SPHINX additionally generalizes to novel viewpoints, visual distractors, spatial arrangements, and execution speeds with a **1.7x** speedup over the most competitive baseline. Our website (http://sphinx-manip.github.io) provides open-sourced code for data collection, training, and evaluation, along with supplementary videos.

The combination of Spiking Neural Networks (SNNs) and Vision Transformers (ViTs) holds potential for achieving both energy efficiency and high performance, particularly suitable for edge vision applications. However, a significant performance gap still exists between SNN-based ViTs and their ANN counterparts. Here, we first analyze why SNN-based ViTs suffer from limited performance and identify a mismatch between the vanilla self-attention mechanism and spatio-temporal spike trains. This mismatch results in degraded spatial relevance and limited temporal interactions. To address these issues, we draw inspiration from biological saccadic attention mechanisms and introduce an innovative Saccadic Spike Self-Attention (SSSA) method. Specifically, in the spatial domain, SSSA employs a novel spike distribution-based method to effectively assess the relevance between Query and Key pairs in SNN-based ViTs. Temporally, SSSA employs a saccadic interaction module that dynamically focuses on selected visual areas at each timestep and significantly enhances whole scene understanding through temporal interactions. Building on the SSSA mechanism, we develop a SNN-based Vision Transformer (SNN-ViT). Extensive experiments across various visual tasks demonstrate that SNN-ViT achieves state-of-the-art performance with linear computational complexity. The effectiveness and efficiency of the SNN-ViT highlight its potential for power-critical edge vision applications.

The blooming of virtual reality and augmented reality (VR/AR) technologies has driven an increasing demand for the creation of high-quality, immersive, and dynamic environments. However, existing generative techniques either focus solely on dynamic objects or perform outpainting from a single perspective image, failing to meet the requirements of VR/AR applications that need free-viewpoint, 360$^{\circ}$ virtual views where users can move in all directions. In this work, we tackle the challenging task of elevating a single panorama to an immersive 4D experience. For the first time, we demonstrate the capability to generate omnidirectional dynamic scenes with 360$^{\circ}$ views at 4K (4096 $\times$ 2048) resolution, thereby providing an immersive user experience. Our method introduces a pipeline that facilitates natural scene animations and optimizes a set of 3D Gaussians using efficient splatting techniques for real-time exploration. To overcome the lack of scene-scale annotated 4D data and models, especially in panoramic formats, we propose a novel Panoramic Denoiser that adapts generic 2D diffusion priors to animate consistently in 360$^{\circ}$ images, transforming them into panoramic videos with dynamic scenes at targeted regions. Subsequently, we propose Dynamic Panoramic Lifting to elevate the panoramic video into a 4D immersive environment while preserving spatial and temporal consistency. By transferring prior knowledge from 2D models in the perspective domain to the panoramic domain and the 4D lifting with spatial appearance and geometry regularization, we achieve high-quality Panorama-to-4D generation at a resolution of 4K for the first time. Project page: https://4k4dgen.github.io/.

The primary focus of most recent works on open-vocabulary neural fields is extracting precise semantic features from the VLMs and then consolidating them efficiently into a multi-view consistent 3D neural fields representation. However, most existing works over-trusted SAM to regularize image-level CLIP without any further refinement. Moreover, several existing works improved efficiency by dimensionality reduction of semantic features from 2D VLMs before fusing with 3DGS semantic fields, which inevitably leads to multi-view inconsistency. In this work, we propose econSG for open-vocabulary semantic segmentation with 3DGS. Our econSG consists of: 1) A Confidence-region Guided Regularization (CRR) that mutually refines SAM and CLIP to get the best of both worlds for precise semantic features with complete and precise boundaries. 2) A low dimensional contextual space to enforce 3D multi-view consistency while improving computational efficiency by fusing backprojected multi-view 2D features and follow by dimensional reduction directly on the fused 3D features instead of operating on each 2D view separately. Our econSG show state-of-the-art performance on four benchmark datasets compared to the existing methods. Furthermore, we are also the most efficient training among all the methods.

Learnable 3D Neural Graphics Representations (3DNGR) have emerged as promising 3D representations for reconstructing 3D scenes from 2D images. Numerous works, including Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and their variants, have significantly enhanced the quality of these representations. The ease of construction from 2D images, suitability for online viewing/sharing, and applications in game/art design downstream tasks make it a vital 3D representation, with potential creation of large numbers of such 3D models. This necessitates large data stores, local or online, to save 3D visual data in these formats. However, no existing framework enables accurate retrieval of stored 3DNGRs. In this work, we propose, Retri3D, a framework that enables accurate and efficient retrieval of 3D scenes represented as NGRs from large data stores using text queries. We introduce a novel Neural Field Artifact Analysis technique, combined with a Smart Camera Movement Module, to select clean views and navigate pre-trained 3DNGRs. These techniques enable accurate retrieval by selecting the best viewing directions in the 3D scene for high-quality visual feature embeddings. We demonstrate that Retri3D is compatible with any NGR representation. On the LERF and ScanNet++ datasets, we show significant improvement in retrieval accuracy compared to existing techniques, while being orders of magnitude faster and storage efficient.

Recent works have attacked person detectors using adversarial patches or static-3D-model-based texture modifications. However, these methods suffer from low attack success rates when faced with significant human movements. The primary challenge stems from the highly non-rigid nature of the human body and clothing. Current attacks fail to model these 3D non-rigid deformations caused by varied actions. Fortunately, recent research has shown significant progress in using NeRF for dynamic human modeling. In this paper, we introduce \texttt{UV-Attack}, a novel physical adversarial attack achieving high attack success rates in scenarios involving extensive and unseen actions. We address the challenges above by leveraging dynamic-NeRF-based UV mapping. Our method can generate human images across diverse actions and viewpoints and even create novel unseen actions by sampling from the SMPL parameter space. While dynamic NeRF models are capable of modeling human bodies, modifying their clothing textures is challenging due to the texture being embedded within neural network parameters. To overcome this, \texttt{UV-Attack} generates UV maps instead of RGB images and modifies the texture stacks. This approach enables real-time texture edits and makes attacks more practical. Finally, we propose a novel Expectation over Pose Transformation loss (EoPT) to improve the evasion success rate on unseen poses and views. Our experiments show that \texttt{UV-Attack} achieves a 92.7\% attack success rate against the FastRCNN model across varied poses in dynamic video settings, significantly outperforming the state-of-the-art AdvCaT attack, which only had a 28.5\% ASR. Moreover, we achieve 49.5\% ASR on the latest YOLOv8 detector in black-box settings. The code is available at https://github.com/PolyLiYJ/UV-Attack

3D Gaussian Splatting (3DGS) is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed. However, 3DGS training currently occurs on a single GPU, limiting its ability to handle high-resolution and large-scale 3D reconstruction tasks due to memory constraints. We introduce Grendel, a distributed system designed to partition 3DGS parameters and parallelize computation across multiple GPUs. As each Gaussian affects a small, dynamic subset of rendered pixels, Grendel employs sparse all-to-all communication to transfer the necessary Gaussians to pixel partitions and performs dynamic load balancing. Unlike existing 3DGS systems that train using one camera view image at a time, Grendel supports batched training with multiple views. We explore various optimization hyperparameter scaling strategies and find that a simple sqrt(batch-size) scaling rule is highly effective. Evaluations using large-scale, high-resolution scenes show that Grendel enhances rendering quality by scaling up 3DGS parameters across multiple GPUs. On the 4K ``Rubble'' dataset, we achieve a test PSNR of 27.28 by distributing 40.4 million Gaussians across 16 GPU, compared to a PSNR of 26.28 using 11.2 million Gaussians on a single GPU. Grendel is an open-source project available at: https://github.com/nyu-systems/Grendel-GS

Decomposing geometry, materials and lighting from a set of images, namely inverse rendering, has been a long-standing problem in computer vision and graphics. Recent advances in neural rendering enable photo-realistic and plausible inverse rendering results. The emergence of 3D Gaussian Splatting has boosted it to the next level by showing real-time rendering potentials. An intuitive finding is that the models used for inverse rendering do not take into account the dependency of opacity w.r.t. material properties, namely cross section, as suggested by optics. Therefore, we develop a novel approach that adds this dependency to the modeling itself. Inspired by radiative transfer, we augment the opacity term by introducing a neural network that takes as input material properties to provide modeling of cross section and a physically correct activation function. The gradients for material properties are therefore not only from color but also from opacity, facilitating a constraint for their optimization. Therefore, the proposed method incorporates more accurate physical properties compared to previous works. We implement our method into 3 different baselines that use Gaussian Splatting for inverse rendering and achieve significant improvements universally in terms of novel view synthesis and material modeling.

Sound plays a major role in human perception. Along with vision, it provides essential information for understanding our surroundings. Despite advances in neural implicit representations, learning acoustics that align with visual scenes remains a challenge. We propose NeRAF, a method that jointly learns acoustic and radiance fields. NeRAF synthesizes both novel views and spatialized room impulse responses (RIR) at new positions by conditioning the acoustic field on 3D scene geometric and appearance priors from the radiance field. The generated RIR can be applied to auralize any audio signal. Each modality can be rendered independently and at spatially distinct positions, offering greater versatility. We demonstrate that NeRAF generates high-quality audio on SoundSpaces and RAF datasets, achieving significant performance improvements over prior methods while being more data-efficient. Additionally, NeRAF enhances novel view synthesis of complex scenes trained with sparse data through cross-modal learning. NeRAF is designed as a Nerfstudio module, providing convenient access to realistic audio-visual generation. Project page: https://amandinebtto.github.io/NeRAF

We present Layout-Your-3D, a framework that allows controllable and compositional 3D generation from text prompts. Existing text-to-3D methods often struggle to generate assets with plausible object interactions or require tedious optimization processes. To address these challenges, our approach leverages 2D layouts as a blueprint to facilitate precise and plausible control over 3D generation. Starting with a 2D layout provided by a user or generated from a text description, we first create a coarse 3D scene using a carefully designed initialization process based on efficient reconstruction models. To enforce coherent global 3D layouts and enhance the quality of instance appearances, we propose a collision-aware layout optimization process followed by instance-wise refinement. Experimental results demonstrate that Layout-Your-3D yields more reasonable and visually appealing compositional 3D assets while significantly reducing the time required for each prompt. Additionally, Layout-Your-3D can be easily applicable to downstream tasks, such as 3D editing and object insertion.

We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement (CPR) framework, GS-CPR. This framework enhances the localization accuracy of state-of-the-art absolute pose regression and scene coordinate regression methods. The 3DGS model renders high-quality synthetic images and depth maps to facilitate the establishment of 2D-3D correspondences. GS-CPR obviates the need for training feature extractors or descriptors by operating directly on RGB images, utilizing the 3D foundation model, MASt3R, for precise 2D matching. To improve the robustness of our model in challenging outdoor environments, we incorporate an exposure-adaptive module within the 3DGS framework. Consequently, GS-CPR enables efficient one-shot pose refinement given a single RGB query and a coarse initial pose estimation. Our proposed approach surpasses leading NeRF-based optimization methods in both accuracy and runtime across indoor and outdoor visual localization benchmarks, achieving new state-of-the-art accuracy on two indoor datasets.

3D Gaussian Splatting (3DGS) has recently emerged as a promising 3D representation. Much research has been focused on reducing its storage requirements and memory footprint. However, the needs to compress and transmit the 3DGS representation to the remote side are overlooked. This new application calls for rate-distortion-optimized 3DGS compression. How to quantize and entropy encode sparse Gaussian primitives in the 3D space remains largely unexplored. Few early attempts resort to the hyperprior framework from learned image compression. But, they fail to utilize fully the inter and intra correlation inherent in Gaussian primitives. Built on ScaffoldGS, this work, termed CAT-3DGS, introduces a context-adaptive triplane approach to their rate-distortion-optimized coding. It features multi-scale triplanes, oriented according to the principal axes of Gaussian primitives in the 3D space, to capture their inter correlation (i.e. spatial correlation) for spatial autoregressive coding in the projected 2D planes. With these triplanes serving as the hyperprior, we further perform channel-wise autoregressive coding to leverage the intra correlation within each individual Gaussian primitive. Our CAT-3DGS incorporates a view frequency-aware masking mechanism. It actively skips from coding those Gaussian primitives that potentially have little impact on the rendering quality. When trained end-to-end to strike a good rate-distortion trade-off, our CAT-3DGS achieves the state-of-the-art compression performance on the commonly used real-world datasets.

Recent point-based object completion methods have demonstrated the ability to accurately recover the missing geometry of partially observed objects. However, these approaches are not well-suited for completing objects within a scene, as they do not consider known scene constraints (e.g., other observed surfaces) in their completions and further expect the partial input to be in a canonical coordinate system, which does not hold for objects within scenes. While instance scene completion methods have been proposed for completing objects within a scene, they lag behind point-based object completion methods in terms of object completion quality and still do not consider known scene constraints during completion. To overcome these limitations, we propose a point cloud-based instance completion model that can robustly complete objects at arbitrary scales and pose in the scene. To enable reasoning at the scene level, we introduce a sparse set of scene constraints represented as point clouds and integrate them into our completion model via a cross-attention mechanism. To evaluate the instance scene completion task on indoor scenes, we further build a new dataset called ScanWCF, which contains labeled partial scans as well as aligned ground truth scene completions that are watertight and collision-free. Through several experiments, we demonstrate that our method achieves improved fidelity to partial scans, higher completion quality, and greater plausibility over existing state-of-the-art methods.

Estimating geometry from dynamic scenes, where objects move and deform over time, remains a core challenge in computer vision. Current approaches often rely on multi-stage pipelines or global optimizations that decompose the problem into subtasks, like depth and flow, leading to complex systems prone to errors. In this paper, we present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes. Our key insight is that by simply estimating a pointmap for each timestep, we can effectively adapt DUSt3R’s representation, previously only used for static scenes, to dynamic scenes. However, this approach presents a significant challenge: the scarcity of suitable training data, namely dynamic, posed videos with depth labels. Despite this, we show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics, even without an explicit motion representation. Based on this, we introduce new optimizations for several downstream video-specific tasks and demonstrate strong performance on video depth and camera pose estimation, outperforming prior work in terms of robustness and efficiency. Moreover, MonST3R shows promising results for primarily feed-forward 4D reconstruction. Interactive 4D results, source code, and trained models are available at: https://monst3r-project.github.io/.

Linear attention has emerged as a promising alternative to softmax-based attention, leveraging kernelized feature maps to reduce complexity from quadratic to linear in sequence length. However, the non-negative constraint on feature maps and the relaxed exponential function used in approximation lead to significant information loss compared to the original query-key dot products, resulting in less discriminative attention maps with higher entropy. To address the missing interactions driven by negative values in query-key pairs, we propose a polarity-aware linear attention mechanism that explicitly models both same-signed and opposite-signed query-key interactions, ensuring comprehensive coverage of relational information. Furthermore, to restore the spiky properties of attention maps, we provide a theoretical analysis proving the existence of a class of element-wise functions (with positive first and second derivatives) that can reduce entropy in the attention distribution. For simplicity, and recognizing the distinct contributions of each dimension, we employ a learnable power function for rescaling, allowing strong and weak attention signals to be effectively separated. Extensive experiments demonstrate that the proposed PolaFormer improves performance on various vision tasks, enhancing both expressiveness and efficiency by up to 4.6%.

Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary information from multiple modalities. MM-FSS employs a shared backbone with two heads to extract intermodal and unimodal visual features, and a pretrained text encoder to generate text embeddings. To fully exploit the multimodal information, we propose a Multimodal Correlation Fusion (MCF) module to generate multimodal correlations, and a Multimodal Semantic Fusion (MSF) module to refine the correlations using text-aware semantic guidance. Additionally, we propose a simple yet effective Test-time Adaptive Cross-modal Calibration (TACC) technique to mitigate training bias, further improving generalization. Experimental results on S3DIS and ScanNet datasets demonstrate significant performance improvements achieved by our method. The efficacy of our approach indicates the benefits of leveraging commonly-ignored free modalities for FS-PCS, providing valuable insights for future research. The code is available at github.com/ZhaochongAn/Multimodality-3D-Few-Shot.

Building interactable replicas of articulated objects is a key challenge in computer vision. Existing methods often fail to effectively integrate information across different object states, limiting the accuracy of part-mesh reconstruction and part dynamics modeling, particularly for complex multi-part articulated objects. We introduce ArtGS, a novel approach that leverages 3D Gaussians as a flexible and efficient representation to address these issues. Our method incorporates canonical Gaussians with coarse-to-fine initialization and updates for aligning articulated part information across different object states, and employs a skinning-inspired part dynamics modeling module to improve both part-mesh reconstruction and articulation learning. Extensive experiments on both synthetic and real-world datasets, including a new benchmark for complex multi-part objects, demonstrate that ArtGS achieves state-of-the-art performance in joint parameter estimation and part mesh reconstruction. Our approach significantly improves reconstruction quality and efficiency, especially for multi-part articulated objects. Additionally, we provide comprehensive analyses of our design choices, validating the effectiveness of each component to highlight potential areas for future improvement.

Implicit functions such as Neural Radiance Fields (NeRFs), occupancy networks, and signed distance functions (SDFs) have become pivotal in computer vision for reconstructing detailed object shapes from sparse views. Achieving optimal performance with these models can be challenging due to the extreme sparsity of inputs and distribution shifts induced by data corruptions. To this end, large, noise-free synthetic datasets can serve as shape priors to help models fill in gaps, but the resulting reconstructions must be approached with caution. Uncertainty estimation is crucial for assessing the quality of these reconstructions, particularly in identifying areas where the model is uncertain about the parts it has inferred from the prior. In this paper, we introduce Dropsembles, a novel method for uncertainty estimation in tuned implicit functions. We demonstrate the efficacy of our approach through a series of experiments, starting with toy examples and progressing to a real-world scenario. Specifically, we train a Convolutional Occupancy Network on synthetic anatomical data and test it on low-resolution MRI segmentations of the lumbar spine. Our results show that Dropsembles achieve the accuracy and calibration levels of deep ensembles but with significantly less computational cost.