ICLR 2025 论文列表

Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, manifesting efficient and high-fidelity novel view synthesis. However, accurately representing surfaces, especially in large and complex scenarios, remains a significant challenge due to the unstructured nature of 3DGS. In this paper, we present CityGaussianV2, a novel approach for large-scale scene reconstruction that addresses critical challenges related to geometric accuracy and efficiency. Building on the favorable generalization capabilities of 2D Gaussian Splatting (2DGS), we address its convergence and scalability issues. Specifically, we implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence. To scale up, we introduce an elongation filter that mitigates Gaussian count explosion caused by 2DGS degeneration. Furthermore, we optimize the CityGaussian pipeline for parallel training, achieving up to 10$\times$ compression, at least 25\% savings in training time, and a 50\% decrease in memory usage. We also established standard geometry benchmarks under large-scale scenes. Experimental results demonstrate that our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.

Spiking neural networks (SNNs) exhibit superior energy efficiency but suffer from limited performance. In this paper, we consider SNNs as ensembles of temporal subnetworks that share architectures and weights, and highlight a crucial issue that affects their performance: excessive differences in initial states (neuronal membrane potentials) across timesteps lead to unstable subnetwork outputs, resulting in degraded performance. To mitigate this, we promote the consistency of the initial membrane potential distribution and output through membrane potential smoothing and temporally adjacent subnetwork guidance, respectively, to improve overall stability and performance. Moreover, membrane potential smoothing facilitates forward propagation of information and backward propagation of gradients, mitigating the notorious temporal gradient vanishing problem. Our method requires only minimal modification of the spiking neurons without adapting the network structure, making our method generalizable and showing consistent performance gains in 1D speech, 2D object, and 3D point cloud recognition tasks. In particular, on the challenging CIFAR10-DVS dataset, we achieved 83.20\% accuracy with only four timesteps. This provides valuable insights into unleashing the potential of SNNs.

Point cloud video perception has become an essential task for the realm of 3D vision. Current 4D representation learning techniques typically engage in iterative processing coupled with dense query operations. Although effective in capturing temporal features, this approach leads to substantial computational redundancy. In this work, we propose a framework, named as PvNeXt, for effective yet efficient point cloud video recognition, via personalized one-shot query operation. Specially, PvNeXt consists of two key modules, the Motion Imitator and the Single-Step Motion Encoder. The former module, the Motion Imitator, is designed to capture the temporal dynamics inherent in sequences of point clouds, thus generating the virtual motion corresponding to each frame. The Single-Step Motion Encoder performs a one-step query operation, associating point cloud of each frame with its corresponding virtual motion frame, thereby extracting motion cues from point cloud sequences and capturing temporal dynamics across the entire sequence. Through the integration of these two modules, {PvNeXt} enables personalized one-shot queries for each frame, effectively eliminating the need for frame-specific looping and intensive query processes. Extensive experiments on multiple benchmarks demonstrate the effectiveness of our method.

Accurate 3D object detection in real-world environments requires a huge amount of annotated data with high quality. Acquiring such data is tedious and expensive, and often needs repeated effort when a new sensor is adopted or when the detector is deployed in a new environment. We investigate a new scenario to construct 3D object detectors: *learning from the predictions of a nearby unit that is equipped with an accurate detector.* For example, when a self-driving car enters a new area, it may learn from other traffic participants whose detectors have been optimized for that area. This setting is label-efficient, sensor-agnostic, and communication-efficient: nearby units only need to share the predictions with the ego agent (e.g., car). Naively using the received predictions as ground-truths to train the detector for the ego car, however, leads to inferior performance. We systematically study the problem and identify viewpoint mismatches and mislocalization (due to synchronization and GPS errors) as the main causes, which unavoidably result in false positives, false negatives, and inaccurate pseudo labels. We propose a distance-based curriculum, first learning from closer units with similar viewpoints and subsequently improving the quality of other units' predictions via self-training. We further demonstrate that an effective pseudo label refinement module can be trained with a handful of annotated data, largely reducing the data quantity necessary to train an object detector. We validate our approach on the recently released real-world collaborative driving dataset, using reference cars' predictions as pseudo labels for the ego car. Extensive experiments including several scenarios (e.g., different sensors, detectors, and domains) demonstrate the effectiveness of our approach toward label-efficient learning of 3D perception from other units' predictions.

Reconstructing pedestrian motion from dynamic sensors, with a focus on pedestrian intention, is crucial for advancing autonomous driving safety. However, this task is challenging due to data limitations arising from technical complexities, safety, and cost concerns. We introduce the Pedestrian Motion Reconstruction (PMR) dataset, which focuses on pedestrian intention to reconstruct behavior using multiple perspectives and modalities. PMR is developed from a mixed reality platform that combines real-world realism with the extensive, accurate labels of simulations, thereby reducing costs and risks. It captures the intricate dynamics of pedestrian interactions with objects and vehicles, using different modalities for a comprehensive understanding of human-vehicle interaction. Analyses show that PMR can naturally exhibit pedestrian intent and simulate extreme cases. PMR features a vast collection of data from 54 subjects interacting across 12 urban settings with 7 objects, encompassing 12,138 sequences with diverse weather conditions and vehicle speeds. This data provides a rich foundation for modeling pedestrian intent through multi-view and multi-modal insights. We also conduct comprehensive benchmark assessments across different modalities to thoroughly evaluate pedestrian motion reconstruction methods.

Breast cancer bone metastasis (BCBM) affects women’s health globally, calling for the development of effective diagnosis and prognosis solutions. While deep learning has exhibited impressive capacities across various healthcare domains, its applicability in BCBM diseases is consistently hindered by the lack of an open, large-scale, deep learning-ready dataset. As such, we introduce the Bone Metastasis (BoneMet) dataset, the first large-scale, publicly available, high-resolution medical resource, which is derived from a well-accepted murine BCBM model. The unique advantage of BoneMet over existing human datasets is repeated sequential scans per subject over the entire disease development phases. The dataset consists of over 67 terabytes of multi-modal medical data, including 2D X-ray images, 3D CT scans, and detailed biological data (e.g., medical records and bone quantitative analysis), collected from more than five hundreds mice spanning from 2019 to 2024. Our BoneMet dataset is well-organized into six components, i.e., Rotation X-Ray, Recon-CT, Seg-CT, Regist-CT, RoI-CT, and MiceMediRec. We further show that BoneMet can be readily adopted to build versatile, large-scale AI models for managing BCBM diseases in terms of diagnosis using 2D or 3D images, prognosis of bone deterioration, and sparse-angle 3D reconstruction for safe long-term disease monitoring. Our preliminary results demonstrate that BoneMet has the potentials to jump-start the development and fine-tuning of AI-driven solutions prior to their applications to human patients. To facilitate its easy access and wide dissemination, we have created the BoneMet package, providing three APIs that enable researchers to (i) flexibly process and download the BoneMet data filtered by specific time frames; and (ii) develop and train large-scale AI models for precise BCBM diagnosis and prognosis. The BoneMet dataset is officially available on Hugging Face Datasets at https://huggingface.co/datasets/BoneMet/BoneMet. The BoneMet package is available on the Python Package Index (PyPI) at https://pypi.org/project/BoneMet. Code and tutorials are available at https://github.com/Tiankuo528/BoneMet.

We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models. Notably, several recent alternative attention mechanisms, including Hyena, Mamba, SimA, Conv2Former, and Castling-ViT, can be viewed as specific instances of our PADRe framework. PADRe leverages polynomial functions and draws upon established results from approximation theory, enhancing computational efficiency without compromising accuracy. PADRe's key components include multiplicative nonlinearities, which we implement using straightforward, hardware-friendly operations such as Hadamard products, incurring only linear computational and memory costs. PADRe further avoids the need for using complex functions such as Softmax, yet it maintains comparable or superior accuracy compared to traditional self-attention. We assess the effectiveness of PADRe as a drop-in replacement for self-attention across diverse computer vision tasks. These tasks include image classification, image-based 2D object detection, and 3D point cloud object detection. Empirical results demonstrate that PADRe runs significantly faster than the conventional self-attention (11x~43x faster on server GPU and mobile NPU) while maintaining similar accuracy when substituting self-attention in the transformer models.

LiDAR-based 3D object detection is crucial for various applications but often experiences performance degradation in real-world deployments due to domain shifts. While most studies focus on cross-dataset shifts, such as changes in environments and object geometries, practical corruptions from sensor variations and weather conditions remain underexplored. In this work, we propose a novel online test-time adaptation framework for 3D detectors that effectively tackles these shifts, including a challenging $\textit{cross-corruption}$ scenario where cross-dataset shifts and corruptions co-occur. By leveraging long-term knowledge from previous test batches, our approach mitigates catastrophic forgetting and adapts effectively to diverse shifts. Specifically, we propose a Model Synergy (MOS) strategy that dynamically selects historical checkpoints with diverse knowledge and assembles them to best accommodate the current test batch. This assembly is directed by our proposed Synergy Weights (SW), which perform a weighted averaging of the selected checkpoints, minimizing redundancy in the composite model. The SWs are computed by evaluating the similarity of predicted bounding boxes on the test data and the independence of features between checkpoint pairs in the model bank. To maintain an efficient and informative model bank, we discard checkpoints with the lowest average SW scores, replacing them with newly updated models. Our method was rigorously tested against existing test-time adaptation strategies across three datasets and eight types of corruptions, demonstrating superior adaptability to dynamic scenes and conditions. Notably, it achieved a 67.3% improvement in a challenging cross-corruption scenario, offering a more comprehensive benchmark for adaptation. Source code: https://github.com/zhuoxiao-chen/MOS.

We present 3D Spatial MultiModal Memory (M3), a multimodal memory system designed to retain information about medium-sized static scenes through video sources for visual perception. By integrating 3D Gaussian Splatting techniques with foundation models, M3 builds a multimodal memory capable of rendering feature representations across granularities, encompassing a wide range of knowledge. In our exploration, we identify two key challenges in previous works on feature splatting: (1) computational constraints in storing high-dimensional features for each Gaussian primitive, and (2) misalignment or information loss between distilled features and foundation model features. To address these challenges, we propose M3 with key components of principal scene components and Gaussian memory attention, enabling efficient training and inference. To validate M3, we conduct comprehensive quantitative evaluations of feature similarity and downstream tasks, as well as qualitative visualizations to highlight the pixel trace of Gaussian memory attention. Our approach encompasses a diverse range of foundation models, including vision-language models (VLMs), perception models, and large multimodal and language models (LMMs/LLMs). Furthermore, to demonstrate real-world applicability, we deploy M3’s feature field in indoor scenes on a quadruped robot. Notably, we claim that M3 is the first work to address the core compression challenges in 3D feature distillation.

Embodied tasks require the agent to fully understand 3D scenes simultaneously with its exploration, so an online, real-time, fine-grained and highly-generalized 3D perception model is desperately needed. Since high-quality 3D data is limited, directly training such a model in 3D is infeasible. Meanwhile, vision foundation models (VFM) has revolutionized the field of 2D computer vision with superior performance, which makes the use of VFM to assist embodied 3D perception a promising direction. However, most existing VFM-assisted 3D perception methods are either offline or too slow that cannot be applied in practical embodied tasks. In this paper, we aim to leverage Segment Anything Model (SAM) for real-time 3D instance segmentation in an online setting. This is a challenging problem since future frames are not available in the input streaming RGB-D video, and an instance may be observed in several frames so efficient object matching between frames is required. To address these challenges, we first propose a geometric-aware query lifting module to represent the 2D masks generated by SAM by 3D-aware queries, which is then iteratively refined by a dual-level query decoder. In this way, the 2D masks are transferred to fine-grained shapes on 3D point clouds. Benefit from the query representation for 3D masks, we can compute the similarity matrix between the 3D masks from different views by efficient matrix operation, which enables real-time inference. Experiments on ScanNet, ScanNet200, SceneNN and 3RScan show our method achieves state-of-the-art performance among online 3D perception models, even outperforming offline VFM-assisted 3D instance segmentation methods by a large margin. Our method also demonstrates great generalization ability in several zero-shot dataset transferring experiments and show great potential in data-efficient setting.

Existing realistic blur datasets provide insufficient variety in scenes and blur patterns to be trained, while expanding data diversity demands considerable time and effort due to complex dual-camera systems. To address the challenge, data augmentation can be an effective way to artificially increase data diversity. However, existing methods on this line are typically designed to estimate motions from a 2D perspective, e.g., estimating 2D non-uniform kernels disregarding 3D aspects of blur modeling, which leads to unrealistic motion patterns due to the fact that camera and object motions inherently arise in 3D space. In this paper, we propose a 3D-aware blur synthesizer capable of generating diverse and realistic blur images for blur data augmentation. Specifically, we estimate 3D camera positions within the motion blur interval, generate the corresponding scene images, and aggregate them to synthesize a realistic blur image. Since the 3D camera positions projected onto the 2D image plane inherently lie in 2D space, we can represent the 3D transformation as a combination of 2D transformation and projected 3D residual component. This allows for 3D transformation without requiring explicit depth measurements, as the 3D residual component is directly estimated via a neural network. Furthermore, our blur synthesizer allows for controllable blur data augmentation by modifying blur magnitude, direction, and scenes, resulting in diverse blur images. As a result, our method significantly improves deblurring performance, making it more practical for real-world scenarios.

Vision Transformer models exhibit immense power yet remain opaque to human understanding, posing challenges and risks for practical applications. While prior research has attempted to demystify these models through input attribution and neuron role analysis, there's been a notable gap in considering layer-level information and the holistic path of information flow across layers. In this paper, we investigate the significance of influential neuron paths within vision Transformers, which is a path of neurons from the model input to output that impacts the model inference most significantly. We first propose a joint influence measure to assess the contribution of a set of neurons to the model outcome. And we further provide a layer-progressive neuron locating approach that efficiently selects the most influential neuron at each layer trying to discover the crucial neuron path from input to output within the target model. Our experiments demonstrate the superiority of our method finding the most influential neuron path along which the information flows, over the existing baseline solutions. Additionally, the neuron paths have illustrated that vision Transformers exhibit some specific inner working mechanism for processing the visual information within the same image category. We further analyze the key effects of these neurons on the image classification task, showcasing that the found neuron paths have already preserved the model capability on downstream tasks, which may also shed some lights on real-world applications like model pruning. The project website including implementation code is available at https://foundation-model-research.github.io/NeuronPath/.

Generating compact and sharply detailed 3D meshes poses a significant challenge for current 3D generative models. Different from extracting dense meshes from neural representation, some recent works try to model the native mesh distribution (i.e., a set of triangles), which generates more compact results as humans crafted. However, due to the complexity and variety of mesh topology, most of these methods are typically limited to generating meshes with simple geometry. In this paper, we introduce a generic and scalable mesh generation framework PivotMesh, which makes an initial attempt to extend the native mesh generation to large-scale datasets. We employ a transformer-based autoencoder to encode meshes into discrete tokens and decode them from face level to vertex level hierarchically. Subsequently, to model the complex typology, our model first learns to generate pivot vertices as coarse mesh representation and then generate the complete mesh tokens with the same auto-regressive Transformer. This reduces the difficulty compared with directly modeling the mesh distribution and further improves the model controllability. PivotMesh demonstrates its versatility by effectively learning from both small datasets like Shapenet, and large-scale datasets like Objaverse and Objaverse-xl. Extensive experiments indicate that PivotMesh can generate compact and sharp 3D meshes across various categories, highlighting its great potential for native mesh modeling.

We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. Prior work in this direction masks out pre-defined frequencies in the input image and employs a reconstruction loss to pre-train the model. While achieving promising results, such an implementation has two fundamental limitations as identified in our paper. First, using pre-defined frequencies overlooks the variability of image frequency responses. Second, pre-trained with frequency-filtered images, the resulting model needs relatively more data to adapt to naturally looking images during fine-tuning. To address these drawbacks, we propose FOurier transform compression with seLf-Knowledge distillation (FOLK), integrating two dedicated ideas. First, inspired by image compression, we adaptively select the masked-out frequencies based on image frequency responses, creating more suitable SSL tasks for pre-training. Second, we employ a two-branch framework empowered by knowledge distillation, enabling the model to take both the filtered and original images as input, largely reducing the burden of downstream tasks. Our experimental results demonstrate the effectiveness of FOLK in achieving competitive performance to many state-of-the-art SSL methods across various downstream tasks, including image classification, few-shot learning, and semantic segmentation.

Generating gestures from human speech has gained tremendous progress in animating virtual avatars. While the existing methods enable synthesizing gestures cooperated by people self-talking, they overlook the practicality of concurrent gesture modeling with two-person interactive conversations. Moreover, the lack of high-quality datasets with concurrent co-speech gestures also limits handling this issue. To fulfill this goal, we first construct a large-scale concurrent co-speech gesture dataset that contains more than 7M frames for diverse two-person interactive posture sequences, dubbed $\textbf{GES-Inter}$. Moreover, we propose Co$^{\mathbf{3}}$Gesture, a novel framework that enables concurrent coherent co-speech gesture synthesis including two-person interactive movements. Our framework is built upon two cooperative generation branches conditioned on decomposed speaker audio. Specifically, to enhance the coordination of human postures w.r.t corresponding speaker audios while interacting with the conversational partner, we present a Temporal-Interaction Module ($\textbf{TIM}$). TIM can effectively model the temporal association representation between two speakers' gesture sequences as interaction guidance and fuse it into the concurrent gesture generation. Then, we devise a mutual attention mechanism to further boost learning dependencies of interacted concurrent motions, thereby enabling us to generate vivid and coherent gestures. Extensive experiments demonstrate that our method outperforms the state-of-the-art models on our newly collected GES-Inter dataset.

Modeling human-like action-to-reaction generation has significant real-world applications, like human-robot interaction and games. Despite recent advancements in single-person motion generation, it is still challenging to well handle action-to-reaction generation, due to the difficulty of directly predicting reaction from action sequence without prompts, and the absence of a unified representation that effectively encodes multi-person motion. To address these challenges, we introduce Think-Then-React (TTR), a large language-model-based framework designed to generate human-like reactions. First, with our fine-grained multimodal training strategy, TTR is capable to unify two processes during inference: a thinking process that explicitly infers action intentions and reasons corresponding reaction description, which serve as semantic prompts, and a reacting process that predicts reactions based on input action and the inferred semantic prompts. Second, to effectively represent multi-person motion in language models, we propose a unified motion tokenizer by decoupling egocentric pose and absolute space features, which effectively represents action and reaction motion with same encoding. Extensive experiments demonstrate that TTR outperforms existing baselines, achieving significant improvements in evaluation metrics, such as reducing FID from 3.988 to 1.942.

Visual perspective taking (VPT) is the ability to perceive and reason about the perspectives of others. It is an essential feature of human intelligence, which develops over the first decade of life and requires an ability to process the 3D structure of visual scenes. A growing number of reports have indicated that deep neural networks (DNNs) become capable of analyzing 3D scenes after training on large image datasets. We investigated if this emergent ability for 3D analysis in DNNs is sufficient for VPT with the 3D perception challenge (3D-PC): a novel benchmark for 3D perception in humans and DNNs. The 3D-PC is comprised of three 3D-analysis tasks posed within natural scene images: (i.) a simple test of object depth order, (ii.) a basic VPT task (VPT-basic), and (iii.) a more challenging version of VPT (VPT-perturb) designed to limit the effectiveness of "shortcut" visual strategies. We tested human participants (N=33) and linearly probed or text-prompted over 300 DNNs on the challenge and found that nearly all of the DNNs approached or exceeded human accuracy in analyzing object depth order. Surprisingly, DNN accuracy on this task correlated with their object recognition performance. In contrast, there was an extraordinary gap between DNNs and humans on VPT-basic. Humans were nearly perfect, whereas most DNNs were near chance. Fine-tuning DNNs on VPT-basic brought them close to human performance, but they, unlike humans, dropped back to chance when tested on VPT-perturb. Our challenge demonstrates that the training routines and architectures of today's DNNs are well-suited for learning basic 3D properties of scenes and objects but are ill-suited for reasoning about these properties like humans do. We release our 3D-PC datasets and code to help bridge this gap in 3D perception between humans and machines.

Set-to-set matching aims to identify correspondences between two sets of unordered items by minimizing a distance metric or maximizing a similarity measure. Traditional metrics, such as Chamfer Distance (CD) and Earth Mover’s Distance (EMD), are widely used for this purpose but often suffer from limitations like suboptimal performance in terms of accuracy and robustness, or high computational costs - or both. In this paper, we propose a novel, simple yet effective set-to-set matching similarity measure, GPS, based on Gumbel prior distributions. These distributions are typically used to model the extrema of samples drawn from various distributions. Our approach is motivated by the observation that the distributions of minimum distances from CD, as encountered in real world applications such as point cloud completion, can be accurately modeled using Gumbel distributions. We validate our method on tasks like few-shot image classification and 3D point cloud completion, demonstrating significant improvements over state of-the-art loss functions across several benchmark datasets. Our demo code is publicly available at https://github.com/Zhang-VISLab/ICLR2025-GPS

DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features in the transformer decoder remain fixed, leading to minimal contributions from later decoder layers, thereby limiting performance improvement. Recently, State Space Models (SSM) have shown efficient context modeling ability with linear complexity through iterative interactions between system states and inputs. Inspired by SSMs, we propose a new 3D object DEtection paradigm with an interactive STate space model (DEST). In the interactive SSM, we design a novel state-dependent SSM parameterization method that enables system states to effectively serve as queries in 3D indoor detection tasks. In addition, we introduce four key designs tailored to the characteristics of point cloud and SSM: The serialization and bidirectional scanning strategies enable bidirectional feature interaction among scene points within the SSM. The inter-state attention mechanism models the relationships between state points, while the gated feed-forward network enhances inter-channel correlations. To the best of our knowledge, this is the first method to model queries as system states and scene points as system inputs, which can simultaneously update scene point features and query features with linear complexity. Extensive experiments on two challenging datasets demonstrate the effectiveness of our DEST-based method. Our method improves the GroupFree baseline in terms of $\text{AP}_{50}$ on ScanNet V2 (+5.3) and SUN RGB-D (+3.2) datasets. Based on the VDETR baseline, Our method sets a new state-of-the-art on the ScanNetV2 and SUN RGB-D datasets.