Abstract:Learning 3D scene representation from a single-view image is a long-standing fundamental problem in computer vision, with the inherent ambiguity in predicting contents unseen from the input view. Built on the recently proposed 3D Gaussian Splatting (3DGS), the Splatter Image method has made promising progress on fast single-image novel view synthesis via learning a single 3D Gaussian for each pixel based on the U-Net feature map of an input image. However, it has limited expressive power to represent occluded components that are not observable in the input view. To address this problem, this paper presents a Hierarchical Splatter Image method in which a pixel is worth more than one 3D Gaussians. Specifically, each pixel is represented by a parent 3D Gaussian and a small number of child 3D Gaussians. Parent 3D Gaussians are learned as done in the vanilla Splatter Image. Child 3D Gaussians are learned via a lightweight Multi-Layer Perceptron (MLP) which takes as input the projected image features of a parent 3D Gaussian and the embedding of a target camera view. Both parent and child 3D Gaussians are learned end-to-end in a stage-wise way. The joint condition of input image features from eyes of the parent Gaussians and the target camera position facilitates learning to allocate child Gaussians to ``see the unseen'', recovering the occluded details that are often missed by parent Gaussians. In experiments, the proposed method is tested on the ShapeNet-SRN and CO3D datasets with state-of-the-art performance obtained, especially showing promising capabilities of reconstructing occluded contents in the input view.
Abstract:Estimating 3D full-body avatars from AR/VR devices is essential for creating immersive experiences in AR/VR applications. This task is challenging due to the limited input from Head Mounted Devices, which capture only sparse observations from the head and hands. Predicting the full-body avatars, particularly the lower body, from these sparse observations presents significant difficulties. In this paper, we are inspired by the inherent property of the kinematic tree defined in the Skinned Multi-Person Linear (SMPL) model, where the upper body and lower body share only one common ancestor node, bringing the potential of decoupled reconstruction. We propose a stratified approach to decouple the conventional full-body avatar reconstruction pipeline into two stages, with the reconstruction of the upper body first and a subsequent reconstruction of the lower body conditioned on the previous stage. To implement this straightforward idea, we leverage the latent diffusion model as a powerful probabilistic generator, and train it to follow the latent distribution of decoupled motions explored by a VQ-VAE encoder-decoder model. Extensive experiments on AMASS mocap dataset demonstrate our state-of-the-art performance in the reconstruction of full-body motions.
Abstract:We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection. Despite remarkable progress witnessed in the field of query-based MV3D object detection, prior art often suffers from either the lack of exploiting high-resolution 2D features in dense attention-based lifting, due to high computational costs, or from insufficiently dense grounding of 3D queries to multi-scale 2D features in sparse attention-based lifting. Our proposed MvACon hits the two birds with one stone using a representationally dense yet computationally sparse attentive feature contextualization scheme that is agnostic to specific 2D-to-3D feature lifting approaches. In experiments, the proposed MvACon is thoroughly tested on the nuScenes benchmark, using both the BEVFormer and its recent 3D deformable attention (DFA3D) variant, as well as the PETR, showing consistent detection performance improvement, especially in enhancing performance in location, orientation, and velocity prediction. It is also tested on the Waymo-mini benchmark using BEVFormer with similar improvement. We qualitatively and quantitatively show that global cluster-based contexts effectively encode dense scene-level contexts for MV3D object detection. The promising results of our proposed MvACon reinforces the adage in computer vision -- ``(contextualized) feature matters".
Abstract:Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, but how wireless communications can support LLMs has not been extensively studied. In this paper, we propose a wireless distributed LLMs paradigm based on Mixture of Experts (MoE), named WDMoE, deploying LLMs collaboratively across edge servers of base station (BS) and mobile devices in the wireless communications system. Specifically, we decompose the MoE layer in LLMs by deploying the gating network and the preceding neural network layer at BS, while distributing the expert networks across the devices. This arrangement leverages the parallel capabilities of expert networks on distributed devices. Moreover, to overcome the instability of wireless communications, we design an expert selection policy by taking into account both the performance of the model and the end-to-end latency, which includes both transmission delay and inference delay. Evaluations conducted across various LLMs and multiple datasets demonstrate that WDMoE not only outperforms existing models, such as Llama 2 with 70 billion parameters, but also significantly reduces end-to-end latency.
Abstract:This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing methods that synthesize texture maps, we propose to generate segment-wise procedural material graphs as the appearance representation, which supports high-quality rendering and provides substantial flexibility in editing. Instead of relying on extensive paired data, i.e., 3D meshes with material graphs and corresponding text descriptions, to train a material graph generative model, we propose to leverage the pre-trained 2D diffusion model as a bridge to connect the text and material graphs. Specifically, our approach decomposes a shape into a set of segments and designs a segment-controlled diffusion model to synthesize 2D images that are aligned with mesh parts. Based on generated images, we initialize parameters of material graphs and fine-tune them through the differentiable rendering module to produce materials in accordance with the textual description. Extensive experiments demonstrate the superior performance of our framework in photorealism, resolution, and editability over existing methods. Project page: https://zhanghe3z.github.io/MaPa/
Abstract:3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with additional points for visually harmonious rendering. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points, whose optimization largely benefits from their initial 3D positions. To this end, we propose to guide the point initialization with an image-conditioned depth completion model, which learns to directly restore the depth map based on the observed image. Such a design allows our model to fill in depth values at an aligned scale with the original depth, and also to harness strong generalizability from largescale diffusion prior. Thanks to the more accurate depth completion, our approach, dubbed InFusion, surpasses existing alternatives with sufficiently better fidelity and efficiency under various complex scenarios. We further demonstrate the effectiveness of InFusion with several practical applications, such as inpainting with user-specific texture or with novel object insertion.
Abstract:Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain. While 2D motion can be intricate, we posit that the underlying 3D motion can often be simple and low-dimensional. In this work, we propose to estimate point trajectories in 3D space to mitigate the issues caused by image projection. Our method, named SpatialTracker, lifts 2D pixels to 3D using monocular depth estimators, represents the 3D content of each frame efficiently using a triplane representation, and performs iterative updates using a transformer to estimate 3D trajectories. Tracking in 3D allows us to leverage as-rigid-as-possible (ARAP) constraints while simultaneously learning a rigidity embedding that clusters pixels into different rigid parts. Extensive evaluation shows that our approach achieves state-of-the-art tracking performance both qualitatively and quantitatively, particularly in challenging scenarios such as out-of-plane rotation.
Abstract:This is only a preview version of GauMesh. Recently, primitive-based rendering has been proven to achieve convincing results in solving the problem of modeling and rendering the 3D dynamic scene from 2D images. Despite this, in the context of novel view synthesis, each type of primitive has its inherent defects in terms of representation ability. It is difficult to exploit the mesh to depict the fuzzy geometry. Meanwhile, the point-based splatting (e.g. the 3D Gaussian Splatting) method usually produces artifacts or blurry pixels in the area with smooth geometry and sharp textures. As a result, it is difficult, even not impossible, to represent the complex and dynamic scene with a single type of primitive. To this end, we propose a novel approach, GauMesh, to bridge the 3D Gaussian and Mesh for modeling and rendering the dynamic scenes. Given a sequence of tracked mesh as initialization, our goal is to simultaneously optimize the mesh geometry, color texture, opacity maps, a set of 3D Gaussians, and the deformation field. At a specific time, we perform $\alpha$-blending on the RGB and opacity values based on the merged and re-ordered z-buffers from mesh and 3D Gaussian rasterizations. This produces the final rendering, which is supervised by the ground-truth image. Experiments demonstrate that our approach adapts the appropriate type of primitives to represent the different parts of the dynamic scene and outperforms all the baseline methods in both quantitative and qualitative comparisons without losing render speed.
Abstract:Transformers have been recently explored for 3D point cloud understanding with impressive progress achieved. A large number of points, over 0.1 million, make the global self-attention infeasible for point cloud data. Thus, most methods propose to apply the transformer in a local region, e.g., spherical or cubic window. However, it still contains a large number of Query-Key pairs, which requires high computational costs. In addition, previous methods usually learn the query, key, and value using a linear projection without modeling the local 3D geometric structure. In this paper, we attempt to reduce the costs and model the local geometry prior by developing a new transformer block, named ConDaFormer. Technically, ConDaFormer disassembles the cubic window into three orthogonal 2D planes, leading to fewer points when modeling the attention in a similar range. The disassembling operation is beneficial to enlarging the range of attention without increasing the computational complexity, but ignores some contexts. To provide a remedy, we develop a local structure enhancement strategy that introduces a depth-wise convolution before and after the attention. This scheme can also capture the local geometric information. Taking advantage of these designs, ConDaFormer captures both long-range contextual information and local priors. The effectiveness is demonstrated by experimental results on several 3D point cloud understanding benchmarks. Code is available at https://github.com/LHDuan/ConDaFormer .
Abstract:Camouflaged objects adaptively fit their color and texture with the environment, which makes them indistinguishable from the surroundings. Current methods revealed that high-level semantic features can highlight the differences between camouflaged objects and the backgrounds. Consequently, they integrate high-level semantic features with low-level detailed features for accurate camouflaged object detection (COD). Unlike previous designs for multi-level feature fusion, we state that enhancing low-level features is more impending for COD. In this paper, we propose an overlapped window cross-level attention (OWinCA) to achieve the low-level feature enhancement guided by the highest-level features. By sliding an aligned window pair on both the highest- and low-level feature maps, the high-level semantics are explicitly integrated into the low-level details via cross-level attention. Additionally, it employs an overlapped window partition strategy to alleviate the incoherence among windows, which prevents the loss of global information. These adoptions enable the proposed OWinCA to enhance low-level features by promoting the separability of camouflaged objects. The associated proposed OWinCANet fuses these enhanced multi-level features by simple convolution operation to achieve the final COD. Experiments conducted on three large-scale COD datasets demonstrate that our OWinCANet significantly surpasses the current state-of-the-art COD methods.