CVPR 2025 Papers

Robotic grasping is a cornerstone capability of embodied systems. Many methods directly output grasps from partial information without modeling the geometry of the scene, leading to suboptimal motion and even collisions. To address these issues, we introduce ZeroGrasp, a novel framework that simultaneously performs 3D reconstruction and grasp pose prediction in near real-time. A key insight of our method is that occlusion reasoning and modeling the spatial relationships between objects is beneficial for both accurate reconstruction and grasping. We couple our method with a novel large-scale synthetic dataset, which comprises 1M photo-realistic images, high-resolution 3D reconstructions and 11.3B physically-valid grasp pose annotations for 12K objects from the Objaverse-LVIS dataset. We evaluate ZeroGrasp on the GraspNet-1B benchmark as well as through real-world robot experiments. ZeroGrasp achieves state-of-the-art performance and generalizes to novel real-world objects by leveraging synthetic data.

This paper introduces ZeroMatch, a novel zero-shot RGB-D point cloud registration framework, aimed at achieving robust 3D matching on unseen data without any task-specific training. Our core idea is to utilize the powerful zero-shot image representation of Stable Diffusion, achieved through extensive pre-training on large-scale data, to enhance point-cloud geometric descriptors for robust matching. Specifically, we combine the handcrafted geometric descriptor FPFH with Stable-Diffusion features to create point descriptors that are both locally and contextually aware, enabling reliable RGB-D registration with zero-shot capability. This approach is based on our observation that Stable-Diffusion features effectively encode discriminative global contextual cues, naturally alleviating the feature ambiguity that FPFH often encounters in scenes with repetitive patterns or low overlap. To further enhance cross-view consistency of Stable-Diffusion features for improved matching, we propose a coupled-image input mode that concatenates the source and target images into a single input, replacing the original single-image mode. This design achieves both inter-image and prompt-to-image consistency attentions, facilitating robust cross-view feature interaction and alignment. Finally, we leverage feature nearest neighbors to construct putative correspondences for hypothesize-and-verify transformation estimation. Extensive experiments on 3DMatch, ScanNet, and ScanLoNet verify the excellent zero-shot matching ability of our method.

Current methods for 3D scene reconstruction from sparse posed images employ intermediate 3D representations such as neural fields, voxel grids, or 3D Gaussians, to achieve multi-view consistent scene appearance and geometry. In this paper we introduce MVGD, a diffusion-based architecture capable of direct pixel-level generation of images and depth maps from novel viewpoints, given an arbitrary number of input views. Our method uses raymap conditioning to both augment visual features with spatial information from different viewpoints, as well as to guide the generation of images and depth maps from novel views. A key aspect of our approach is the multi-task generation of images and depth maps, using learnable task embeddings to guide the diffusion process towards specific modalities. We train this model on a collection of more than 60 million multi-view samples from publicly available datasets, and propose techniques to enable efficient and consistent learning in such diverse conditions. We also propose a novel strategy that enables the efficient training of larger models by incrementally fine-tuning smaller ones, with promising scaling behavior. Through extensive experiments, we report state-of-the-art results in multiple novel view synthesis benchmarks, as well as multi-view stereo and video depth estimation.

Vision Transformers (ViTs) have experienced significant progress and are quantized for deployment in resource-constrained applications. Quantized models are vulnerable to targeted bit-flip attacks (BFAs). A targeted BFA prepares a trigger and a corresponding Trojan/backdoor, inserting the latter (with RowHammer bit flipping) into a victim model, to mislead its classification on samples containing the trigger. Existing targeted BFAs on quantized ViTs are limited in that: (1) they require numerous bit-flips, and (2) the separation between flipped bits is below 4 KB, making attacks infeasible with RowHammer in real-world scenarios. We propose a new and practical targeted attack Flip-S against quantized ViTs. The core insight is that in quantized models, a scale factor change ripples through a batch of model weights. Consequently, flipping bits in scale factors, rather than solely in model weights, enables more cost-effective attacks. We design a Scale-Factor-Search (SFS) algorithm to identify critical bits in scale factors for flipping, and adopt a mutual exclusion strategy to guarantee a 4 KB separation between flips. We evaluate Flip-S on CIFAR-10 and ImageNet datasets across five ViT architectures and two quantization levels. Results show that Flip-S achieves attack success rate (ASR) exceeding 90.0% on all models with 50 bits flipped, outperforming baselines with ASR typically below 80.0%. Furthermore, compared to the SOTA, Flip-S reduces the number of required bit-flips by 8x-20xwhile reaching equal or higher ASR. Our source code is publicly available.

Large Multimodal Models (e.g., GPT-4, Gemini, Chameleon) have evolved into powerful tools with millions of users. However, they remain generic models and lack personalized knowledge of specific user concepts. Previous work has explored personalization for text generation, yet it remains unclear how these methods can be adapted to new modalities, such as image generation. In this paper, we introduce Yo'Chameleon, the first attempt to study personalization for large multimodal models. Given 3-5 images of a particular concept, Yo'Chameleon leverages soft-prompt tuning to embed subject-specific information to (i) answer questions about the subject and (ii) recreate pixel-level details to produce images of the subject in new contexts. Yo'Chameleon is trained with (i) a self-prompting optimization mechanism to balance performance across multiple modalities, and (ii) a "soft-positive" image generation approach to enhance image quality in a few-shot setting. Our qualitative and quantitative analyses reveal that Yo'Chameleon can learn concepts more efficiently using fewer tokens and effectively encode visual attributes, outperforming prompting baselines.

This paper addresses a challenging question: how can we efficiently create high-quality, wide-scope 3D scenes from a single arbitrary image?Existing methods face several constraints, such as requiring multi-view data, time-consuming per-scene optimization, low visual quality, and distorted reconstructions for unseen areas. We propose a novel pipeline to overcome these limitations.Specifically, we introduce a large-scale reconstruction model that uses latents from a video diffusion model to predict 3D Gaussian Splatting, even from a single-condition image, in a feed-forward manner. The video diffusion model is designed to precisely follow a specified camera trajectory, allowing it to generate compressed latents that contain multi-view information while maintaining 3D consistency.We further train the 3D reconstruction model to operate on the video latent space with a progressive training strategy, enabling the generation of high-quality, wide-scope, and generic 3D scenes.Extensive evaluations on various datasets show that our model significantly outperforms existing methods for single-view 3D rendering, particularly with out-of-domain images. For the first time, we demonstrate that a 3D reconstruction model can be effectively built upon the latent space of a diffusion model to realize efficient 3D scene generation.

We present WildGS-SLAM, a robust and efficient monocular RGB SLAM system designed to handle dynamic environments by leveraging uncertainty-aware geometric mapping. Unlike traditional SLAM systems, which assume static scenes, our approach integrates depth and uncertainty information to enhance tracking, mapping, and rendering performance in the presence of moving objects. We introduce an uncertainty map, predicted by a shallow multi-layer perceptron and DINOv2 features, to guide dynamic object removal during both tracking and mapping.This uncertainty map enhances dense bundle adjustment and Gaussian map optimization, improving reconstruction accuracy. Our system is evaluated on multiple datasets and demonstrates artifact-free view synthesis. Results showcase WildGS-SLAM's superior performance in dynamic environments compared to state-of-the-art methods.

3D scene perception demands a large amount of adverse-weather LiDAR data, yet the cost of LiDAR data collection presents a significant scaling-up challenge. To this end, a series of LiDAR simulators have been proposed. Yet, they can only simulate a single adverse weather with a single physical model, and the fidelity is quite limited. This paper presents **WeatherGen**, the first unified diverse-weather LiDAR data diffusion generation framework, significantly improving fidelity. Specifically, we first design a map-based data producer, which is capable of providing a vast amount of high-quality diverse-weather data for training purposes. Then, we utilize the diffusion-denoising paradigm to construct a diffusion model. Among them, we propose a spider mamba generator with the spider mamba scan to restore the disturbed diverse weather data gradually. The spider mamba models the feature interactions by scanning the LiDAR beam circle and central ray, excellently maintaining the physical structure of the LiDAR point cloud. Subsequently, we design a latent domain aligner following the generator to transfer real-world knowledge. Afterward, we devise a contrastive learning-based controller, which equips weather control signals with compact semantic knowledge through language supervision from CLIP, guiding the diffusion model in generating more discriminative data. Finally, we fine-tune WeatherGen with small-scale real-world data to further enhance its performance. Extensive evaluations on KITTI-360 and Seeing Through Fog demonstrate the high generation quality of WeatherGen. Through WeatherGen, we construct the mini-weather dataset, promoting the performance of the downstream task under adverse weather conditions.

Recent advancements in camera-based occupancy prediction have focused on the simultaneous prediction of 3D semantics and scene flow, a task that presents significant challenges due to specific difficulties, e.g., occlusions and unbalanced dynamic environments. In this paper, we analyze these challenges and their underlying causes. To address them, we propose a novel regularization framework called VoxelSplat. This framework leverages recent developments in 3D Gaussian Splatting to enhance model performance in two key ways: (i)Enhanced Semantics Supervision through 2D Projection: During training, our method decodes sparse semantic 3D Gaussians from 3D representations and projects them onto the 2D camera view. This provides additional supervision signals in the camera-visible space, allowing 2D labels to improve the learning of 3D semantics. (ii) Scene Flow Learning: Our framework uses the predicted scene flow to model the motion of Gaussians, and is thus able to learn the scene flow of moving objects in a self-supervised manner using the labels of adjacent frames. Our method can be seamlessly integrated into various existing occupancy models, enhancingperformance without increasing inference time. Extensive experiments on benchmark datasets demonstrate the effectiveness of VoxelSplat in improving the accuracy of both semantic occupancy and scene flow estimation. The project page and codes are available at https://zzy816.github.io/VoxelSplat-Demo/.

Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We show that splatting and its approximations are unnecessary, even within a rasterizer; we instead volumetrically integrate 3D Gaussians directly to compute the transmittance across them analytically. We use this analytic transmittance to derive more physically accurate alpha values than 3DGS, which can directly be used within their framework. The result is a method that more closely follows the volume rendering equation (similar to ray tracing) while enjoying the speed benefits of rasterization. Our method represents opaque surfaces with higher accuracy and fewer points than 3DGS. This enables it to outperform 3DGS for view synthesis (measured in SSIM and LPIPS). Being volumetrically consistent also enables our method to work out of the box for tomography. We match the state-of-the-art 3DGS-based tomography method with fewer points. Our code is publicly available at: https://github.com/chinmay0301ucsd/Vol3DGS

This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that employ neural rendering with explicit depth supervision, VisionPAD utilizes more efficient 3D Gaussian Splatting to reconstruct multi-view representations using only images as supervision. Specifically, we introduce a self-supervised method for voxel velocity estimation. By warping voxels to adjacent frames and supervising the rendered outputs, the model effectively learns motion cues in the sequential data. Furthermore, we adopt a multi-frame photometric consistency approach to enhance geometric perception. It projects adjacent frames to the current frame based on rendered depths and relative poses, boosting the 3D geometric representation through pure image supervision. Extensive experiments on autonomous driving datasets demonstrate that VisionPAD significantly improves performance in 3D object detection, occupancy prediction and map segmentation, surpassing state-of-the-art pre-training strategies by a considerable margin.

Depth estimation is a core problem in robotic perception and vision tasks, but 3D reconstruction from a single image presents inherent uncertainties. Current depth estimation models primarily rely on inter-image relationships for supervised training, often overlooking the intrinsic information provided by the camera itself. We propose a method that embodies the camera model and its physical characteristics into a deep learning model, computing embodied scene depth through real-time interactions with road environments. The model can calculate embodied scene depth in real-time based on immediate environmental changes using only the intrinsic properties of the camera, without any additional equipment. By combining embodied scene depth with RGB image features, the model gains a comprehensive perspective on both geometric and visual details. Additionally, we incorporate text descriptions containing environmental content and depth information as priors for scene understanding, enriching the model's perception of objects. This integration of image and language -- two inherently ambiguous modalities -- leverages their complementary strengths for monocular depth estimation. The real-time nature of the embodied language and depth prior model ensures that the model can continuously adjust its perception and behavior in dynamic environments. Experimental results show that the embodied depth estimation method enhances model performance across different scenes.

Recent advances in human motion prediction (HMP) have shifted focus from isolated motion data to integrating human-scene correlations. In particular, the latest methods leverage human gaze points, using their spatial coordinates to indicate intent--where a person might move within a 3D environment. Despite promising trajectory results, these methods often produce inaccurate poses by overlooking the semantic implications of gaze, specifically the affordances of observed objects, which indicate the possible interactions. To address this, we propose GAP3DS, an affordance-aware HMP model that utilizes gaze-informed object affordances to improve HMP in complex 3D environments. GAP3DS incorporates a gaze-guided affordance learner to identify relevant objects in the scene and infer their affordances based on human gaze, thus contextualizing future human-object interactions. This affordance information, enriched with visual features and gaze data, conditions the generation of multiple human-object interaction poses, which are subsequently decoded into final motion predictions. Extensive experiments on two real-world datasets demonstrate that GAP3DS outperforms state-of-the-art methods in both trajectory and pose accuracy, producing more physically consistent and contextually grounded predictions. For more details and code, please refer to the project page.

Neural implicit surface representation methods have recently shown impressive 3D reconstruction results. However, existing solutions struggle to reconstruct driving scenes due to their large size, highly complex nature and limited visual observation overlap.Hence, to achieve accurate reconstructions, additional supervision data such as LiDAR, strong geometric priors, and long training times are required.To tackle such limitations, we present ViiNeuS, a new hybrid implicit surface learning method that efficiently initializes the signed distance field to reconstruct large driving scenes from 2D street view images.ViiNeuS's hybrid architecture models two separate implicit fields: one representing the volumetric density of the scene, and another one representing the signed distance to the surface.To accurately reconstruct urban outdoor driving scenarios, we introduce a novel volume-rendering strategy that relies on self-supervised probabilistic density estimation to sample points near the surface and transition progressively from volumetric to surface representation. Our solution permits a proper and fast initialization of the signed distance field without relying on any geometric prior on the scene, compared to concurrent methods.By conducting extensive experiments on four outdoor driving datasets, we show that ViiNeuS can learn an accurate and detailed 3D surface scene representation in various driving scenarios while being two times faster to train compared to previous state-of-the-art solutions.

Generative methods for image and video editing use generative models as priors to perform edits despite incomplete information, such as changing the composition of 3D objects shown in a single image. Recent methods have shown promising composition editing results in the image setting, but in the video setting, editing methods have focused on editing object appearance, object motion, or camera motion, and as a result, methods to edit object composition in videos are still missing. We propose VideoHandles as a method for editing 3D object compositions in videos of static scenes with camera motion. Our approach allows editing the 3D position of a 3D object across all frames of a video in a temporally consistent manner. This is achieved by lifting intermediate features of a generative model to a 3D reconstruction that is shared between all frames, editing the reconstruction, and projecting the features on the edited reconstruction back to each frame. To the best of our knowledge, this is the first generative approach to edit object compositions in videos. Our approach is simple and training-free, while outperforming state-of-the-art image editing baselines.

The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly impacted various multimodal tasks. However, these models face challenges in tasks that require spatial understanding within 3D environments. Efforts to enhance MLLMs, such as incorporating point cloud features, have been made, yet a considerable gap remains between the models' learned representations and the inherent complexity of 3D scenes. This discrepancy largely stems from the training of MLLMs on predominantly 2D data, which restricts their effectiveness in comprehending 3D spaces. To address this issue, in this paper, we propose a novel generalist model, i.e., Video-3D LLM, for 3D scene understanding. By treating 3D scenes as dynamic videos and incorporating 3D position encoding into these representations, our Video-3D LLM aligns video representations with real-world spatial contexts more accurately. In addition, we have implemented a maximum coverage sampling technique to optimize the trade-off between computational cost and performance. Extensive experiments demonstrate that our model achieves state-of-the-art performance on several 3D scene understanding benchmarks, including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D.

We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a step forward in 3D computer vision, where models have typically been constrained to and specialized for single tasks. It is also simple and efficient, reconstructing images in under one second, and still outperforming alternatives that require post-processing with visual geometry optimization techniques. The network achieves state-of-the-art results in multiple 3D tasks, including camera parameter estimation, multi-view depth estimation, dense point cloud reconstruction, and 3D point tracking. We also show that using pretrained VGGT as a feature backbone significantly enhances downstream tasks, such as non-rigid point tracking and feed-forward novel view synthesis. Code and models are publicly available at https://github.com/facebookresearch/vggt.

Light field microscopy (LFM) has gained significant attention due to its ability to capture snapshot-based, large-scale 3D fluorescence images. However, existing LFM reconstruction algorithms are highly sensitive to sensor noise or require hard-to-get ground-truth annotated data for training. To address these challenges, this paper introduces V2V3D, an unsupervised view2view-based framework that establishes a new paradigm for joint optimization of image denoising and 3D reconstruction in a unified architecture. We assume that the LF images are derived from a consistent 3D signal, with the noise in each view being independent. This enables V2V3D to incorporate the principle of noise2noise for effective denoising. To enhance the recovery of high-frequency details, we propose a novel wave-optics-based feature alignment technique, which transforms the point spread function, used for forward propagation in wave optics, into convolution kernels specifically designed for feature alignment. Moreover, we introduce an LFM dataset containing LF images and their corresponding 3D intensity volumes. Extensive experiments demonstrate that our approach achieves high computational efficiency and outperforms the other state-of-the-art methods. These advancements position V2V3D as a promising solution for 3D imaging under challenging conditions. Our code and dataset will be publicly accessible at https://joey1998hub.github.io/V2V3D/.

In real-world environments, a LiDAR point cloud registration method with robust generalization capabilities (across varying distances and datasets) is crucial for ensuring safety in autonomous driving and other LiDAR-based applications. However, current methods fall short in achieving this level of generalization. To address these limitations, we propose UGP, a pruned framework designed to enhance generalization power for LiDAR point cloud registration. The core insight in UGP is the elimination of cross-attention mechanisms to improve generalization, allowing the network to concentrate on intra-frame feature extraction. Additionally, we introduce a progressive self-attention module to reduce ambiguity in large-scale scenes and integrate Bird's Eye View (BEV) features to incorporate semantic information about scene elements. Together, these enhancements significantly boost the network's generalization performance. We validated our approach through various generalization experiments in multiple outdoor scenes. In cross-distance generalization experiments on KITTI and nuScenes, UGP achieved state-of-the-art mean Registration Recall rates of 94.5% and 91.4%, respectively. In cross-dataset generalization from nuScenes to KITTI, UGP achieved a state-of-the-art mean Registration Recall of 90.9%.