Abstract:Recent advances in auto-regressive transformers have revolutionized generative modeling across different domains, from language processing to visual generation, demonstrating remarkable capabilities. However, applying these advances to 3D generation presents three key challenges: the unordered nature of 3D data conflicts with sequential next-token prediction paradigm, conventional vector quantization approaches incur substantial compression loss when applied to 3D meshes, and the lack of efficient scaling strategies for higher resolution latent prediction. To address these challenges, we introduce MAR-3D, which integrates a pyramid variational autoencoder with a cascaded masked auto-regressive transformer (Cascaded MAR) for progressive latent upscaling in the continuous space. Our architecture employs random masking during training and auto-regressive denoising in random order during inference, naturally accommodating the unordered property of 3D latent tokens. Additionally, we propose a cascaded training strategy with condition augmentation that enables efficiently up-scale the latent token resolution with fast convergence. Extensive experiments demonstrate that MAR-3D not only achieves superior performance and generalization capabilities compared to existing methods but also exhibits enhanced scaling capabilities compared to joint distribution modeling approaches (e.g., diffusion transformers).
Abstract:We introduce TreeMeshGPT, an autoregressive Transformer designed to generate high-quality artistic meshes aligned with input point clouds. Instead of the conventional next-token prediction in autoregressive Transformer, we propose a novel Autoregressive Tree Sequencing where the next input token is retrieved from a dynamically growing tree structure that is built upon the triangle adjacency of faces within the mesh. Our sequencing enables the mesh to extend locally from the last generated triangular face at each step, and therefore reduces training difficulty and improves mesh quality. Our approach represents each triangular face with two tokens, achieving a compression rate of approximately 22% compared to the naive face tokenization. This efficient tokenization enables our model to generate highly detailed artistic meshes with strong point cloud conditioning, surpassing previous methods in both capacity and fidelity. Furthermore, our method generates mesh with strong normal orientation constraints, minimizing flipped normals commonly encountered in previous methods. Our experiments show that TreeMeshGPT enhances the mesh generation quality with refined details and normal orientation consistency.
Abstract:3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especially in environments with dynamic objects and distractors, the method suffers from floating artifacts and color errors due to inconsistency from different viewpoints. To address this challenge, we propose Multi-View Consistency Gaussian Splatting for the domain of Robust Surface Reconstruction (\textbf{MVGSR}), which takes advantage of lightweight Gaussian models and a {heuristics-guided distractor masking} strategy for robust surface reconstruction in non-static environments. Compared to existing methods that rely on MLPs for distractor segmentation strategies, our approach separates distractors from static scene elements by comparing multi-view feature consistency, allowing us to obtain precise distractor masks early in training. Furthermore, we introduce a pruning measure based on multi-view contributions to reset transmittance, effectively reducing floating artifacts. Finally, a multi-view consistency loss is applied to achieve high-quality performance in surface reconstruction tasks. Experimental results demonstrate that MVGSR achieves competitive geometric accuracy and rendering fidelity compared to the state-of-the-art surface reconstruction algorithms. More information is available on our project page (\href{https://mvgsr.github.io}{this url})
Abstract:Large multimodal models (LMMs) excel in scene understanding but struggle with fine-grained spatiotemporal reasoning due to weak alignment between linguistic and visual representations. Existing methods map textual positions and durations into the visual space encoded from frame-based videos, but suffer from temporal sparsity that limits language-vision temporal coordination. To address this issue, we introduce LLaFEA (Large Language and Frame-Event Assistant) to leverage event cameras for temporally dense perception and frame-event fusion. Our approach employs a cross-attention mechanism to integrate complementary spatial and temporal features, followed by self-attention matching for global spatio-temporal associations. We further embed textual position and duration tokens into the fused visual space to enhance fine-grained alignment. This unified framework ensures robust spatio-temporal coordinate alignment, enabling LMMs to interpret scenes at any position and any time. In addition, we construct a dataset of real-world frames-events with coordinate instructions and conduct extensive experiments to validate the effectiveness of the proposed method.
Abstract:We introduce DuCos, a novel depth super-resolution framework grounded in Lagrangian duality theory, offering a flexible integration of multiple constraints and reconstruction objectives to enhance accuracy and robustness. Our DuCos is the first to significantly improve generalization across diverse scenarios with foundation models as prompts. The prompt design consists of two key components: Correlative Fusion (CF) and Gradient Regulation (GR). CF facilitates precise geometric alignment and effective fusion between prompt and depth features, while GR refines depth predictions by enforcing consistency with sharp-edged depth maps derived from foundation models. Crucially, these prompts are seamlessly embedded into the Lagrangian constraint term, forming a synergistic and principled framework. Extensive experiments demonstrate that DuCos outperforms existing state-of-the-art methods, achieving superior accuracy, robustness, and generalization. The source codes and pre-trained models will be publicly available.
Abstract:Moving object segmentation plays a crucial role in understanding dynamic scenes involving multiple moving objects, while the difficulties lie in taking into account both spatial texture structures and temporal motion cues. Existing methods based on video frames encounter difficulties in distinguishing whether pixel displacements of an object are caused by camera motion or object motion due to the complexities of accurate image-based motion modeling. Recent advances exploit the motion sensitivity of novel event cameras to counter conventional images' inadequate motion modeling capabilities, but instead lead to challenges in segmenting pixel-level object masks due to the lack of dense texture structures in events. To address these two limitations imposed by unimodal settings, we propose the first instance-level moving object segmentation framework that integrates complementary texture and motion cues. Our model incorporates implicit cross-modal masked attention augmentation, explicit contrastive feature learning, and flow-guided motion enhancement to exploit dense texture information from a single image and rich motion information from events, respectively. By leveraging the augmented texture and motion features, we separate mask segmentation from motion classification to handle varying numbers of independently moving objects. Through extensive evaluations on multiple datasets, as well as ablation experiments with different input settings and real-time efficiency analysis of the proposed framework, we believe that our first attempt to incorporate image and event data for practical deployment can provide new insights for future work in event-based motion related works. The source code with model training and pre-trained weights is released at https://npucvr.github.io/EvInsMOS
Abstract:Identifying affordance regions on 3D objects from semantic cues is essential for robotics and human-machine interaction. However, existing 3D affordance learning methods struggle with generalization and robustness due to limited annotated data and a reliance on 3D backbones focused on geometric encoding, which often lack resilience to real-world noise and data corruption. We propose GEAL, a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging large-scale pre-trained 2D models. We employ a dual-branch architecture with Gaussian splatting to establish consistent mappings between 3D point clouds and 2D representations, enabling realistic 2D renderings from sparse point clouds. A granularity-adaptive fusion module and a 2D-3D consistency alignment module further strengthen cross-modal alignment and knowledge transfer, allowing the 3D branch to benefit from the rich semantics and generalization capacity of 2D models. To holistically assess the robustness, we introduce two new corruption-based benchmarks: PIAD-C and LASO-C. Extensive experiments on public datasets and our benchmarks show that GEAL consistently outperforms existing methods across seen and novel object categories, as well as corrupted data, demonstrating robust and adaptable affordance prediction under diverse conditions. Code and corruption datasets have been made publicly available.
Abstract:Existing research has made impressive strides in reconstructing human facial shapes and textures from images with well-illuminated faces and minimal external occlusions. Nevertheless, it remains challenging to recover accurate facial textures from scenarios with complicated illumination affected by external occlusions, e.g. a face that is partially obscured by items such as a hat. Existing works based on the assumption of single and uniform illumination cannot correctly process these data. In this work, we introduce a novel approach to model 3D facial textures under such unnatural illumination. Instead of assuming single illumination, our framework learns to imitate the unnatural illumination as a composition of multiple separate light conditions combined with learned neural representations, named Light Decoupling. According to experiments on both single images and video sequences, we demonstrate the effectiveness of our approach in modeling facial textures under challenging illumination affected by occlusions. Please check https://tianxinhuang.github.io/projects/Deface for our videos and codes.
Abstract:Event cameras offer unparalleled advantages for real-time perception in dynamic environments, thanks to their microsecond-level temporal resolution and asynchronous operation. Existing event-based object detection methods, however, are limited by fixed-frequency paradigms and fail to fully exploit the high-temporal resolution and adaptability of event cameras. To address these limitations, we propose FlexEvent, a novel event camera object detection framework that enables detection at arbitrary frequencies. Our approach consists of two key components: FlexFuser, an adaptive event-frame fusion module that integrates high-frequency event data with rich semantic information from RGB frames, and FAL, a frequency-adaptive learning mechanism that generates frequency-adjusted labels to enhance model generalization across varying operational frequencies. This combination allows our method to detect objects with high accuracy in both fast-moving and static scenarios, while adapting to dynamic environments. Extensive experiments on large-scale event camera datasets demonstrate that our approach surpasses state-of-the-art methods, achieving significant improvements in both standard and high-frequency settings. Notably, our method maintains robust performance when scaling from 20 Hz to 90 Hz and delivers accurate detection up to 180 Hz, proving its effectiveness in extreme conditions. Our framework sets a new benchmark for event-based object detection and paves the way for more adaptable, real-time vision systems.
Abstract:Realistic scene reconstruction in driving scenarios poses significant challenges due to fast-moving objects. Most existing methods rely on labor-intensive manual labeling of object poses to reconstruct dynamic objects in canonical space and move them based on these poses during rendering. While some approaches attempt to use 3D object trackers to replace manual annotations, the limited generalization of 3D trackers -- caused by the scarcity of large-scale 3D datasets -- results in inferior reconstructions in real-world settings. In contrast, 2D foundation models demonstrate strong generalization capabilities. To eliminate the reliance on 3D trackers and enhance robustness across diverse environments, we propose a stable object tracking module by leveraging associations from 2D deep trackers within a 3D object fusion strategy. We address inevitable tracking errors by further introducing a motion learning strategy in an implicit feature space that autonomously corrects trajectory errors and recovers missed detections. Experimental results on Waymo-NOTR datasets show we achieve state-of-the-art performance. Our code will be made publicly available.