Gang Zeng

Min Zhong, Xinghao Chen, Xiaokang Chen et al.

This paper studies the 3D instance segmentation problem, which has a variety of real-world applications such as robotics and augmented reality. Since the surroundings of 3D objects are of high complexity, the separating of different objects is very difficult. To address this challenging problem, we propose a novel framework to group and refine the 3D instances. In practice, we first learn an offset vector for each point and shift it to its predicted instance center. To better group these points, we propose a Hierarchical Point Grouping algorithm to merge the centrally aggregated points progressively. All points are grouped into small clusters, which further gradually undergo another clustering procedure to merge into larger groups. These multi-scale groups are exploited for instance prediction, which is beneficial for predicting instances with different scales. In addition, a novel MaskScoreNet is developed to produce binary point masks of these groups for further refining the segmentation results. Extensive experiments conducted on the ScanNetV2 and S3DIS benchmarks demonstrate the effectiveness of the proposed method. For instance, our approach achieves a 66.4\% mAP with the 0.5 IoU threshold on the ScanNetV2 test set, which is 1.9\% higher than the state-of-the-art method.

Xian Liu, Xiaohang Zhan, Jiaxiang Tang et al.

Realistic 3D human generation from text prompts is a desirable yet challenging task. Existing methods optimize 3D representations like mesh or neural fields via score distillation sampling (SDS), which suffers from inadequate fine details or excessive training time. In this paper, we propose an efficient yet effective framework, HumanGaussian, that generates high-quality 3D humans with fine-grained geometry and realistic appearance. Our key insight is that 3D Gaussian Splatting is an efficient renderer with periodic Gaussian shrinkage or growing, where such adaptive density control can be naturally guided by intrinsic human structures. Specifically, 1) we first propose a Structure-Aware SDS that simultaneously optimizes human appearance and geometry. The multi-modal score function from both RGB and depth space is leveraged to distill the Gaussian densification and pruning process. 2) Moreover, we devise an Annealed Negative Prompt Guidance by decomposing SDS into a noisier generative score and a cleaner classifier score, which well addresses the over-saturation issue. The floating artifacts are further eliminated based on Gaussian size in a prune-only phase to enhance generation smoothness. Extensive experiments demonstrate the superior efficiency and competitive quality of our framework, rendering vivid 3D humans under diverse scenarios. Project Page: https://alvinliu0.github.io/projects/HumanGaussian

Jiaxiang Tang, Zhaoshuo Li, Zekun Hao et al.

Current auto-regressive mesh generation methods suffer from issues such as incompleteness, insufficient detail, and poor generalization. In this paper, we propose an Auto-regressive Auto-encoder (ArAE) model capable of generating high-quality 3D meshes with up to 4,000 faces at a spatial resolution of $512^3$. We introduce a novel mesh tokenization algorithm that efficiently compresses triangular meshes into 1D token sequences, significantly enhancing training efficiency. Furthermore, our model compresses variable-length triangular meshes into a fixed-length latent space, enabling training latent diffusion models for better generalization. Extensive experiments demonstrate the superior quality, diversity, and generalization capabilities of our model in both point cloud and image-conditioned mesh generation tasks.

Depu Meng, Xiaokang Chen, Zejia Fan et al.

The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Our approach is motivated by that the cross-attention in DETR relies highly on the content embeddings for localizing the four extremities and predicting the box, which increases the need for high-quality content embeddings and thus the training difficulty. Our approach, named conditional DETR, learns a conditional spatial query from the decoder embedding for decoder multi-head cross-attention. The benefit is that through the conditional spatial query, each cross-attention head is able to attend to a band containing a distinct region, e.g., one object extremity or a region inside the object box. This narrows down the spatial range for localizing the distinct regions for object classification and box regression, thus relaxing the dependence on the content embeddings and easing the training. Empirical results show that conditional DETR converges 6.7x faster for the backbones R50 and R101 and 10x faster for stronger backbones DC5-R50 and DC5-R101. Code is available at https://github.com/Atten4Vis/ConditionalDETR.

Xiaokang Chen, Yuhui Yuan, Gang Zeng et al.

In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on two segmentation networks perturbed with different initialization for the same input image. The pseudo one-hot label map, output from one perturbed segmentation network, is used to supervise the other segmentation network with the standard cross-entropy loss, and vice versa. The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels. Experiment results show that our approach achieves the state-of-the-art semi-supervised segmentation performance on Cityscapes and PASCAL VOC 2012. Code is available at https://git.io/CPS.

Falong Shen, Shuicheng Yan, Gang Zeng

In this paper we propose a new method to get the specified network parameters through one time feed-forward propagation of the meta networks and explore the application to neural style transfer. Recent works on style transfer typically need to train image transformation networks for every new style, and the style is encoded in the network parameters by enormous iterations of stochastic gradient descent. To tackle these issues, we build a meta network which takes in the style image and produces a corresponding image transformations network directly. Compared with optimization-based methods for every style, our meta networks can handle an arbitrary new style within $19ms$ seconds on one modern GPU card. The fast image transformation network generated by our meta network is only 449KB, which is capable of real-time executing on a mobile device. We also investigate the manifold of the style transfer networks by operating the hidden features from meta networks. Experiments have well validated the effectiveness of our method. Code and trained models has been released https://github.com/FalongShen/styletransfer.

Jiaxiang Tang, Ruijie Lu, Xiaokang Chen et al.

Text-to-texture synthesis has become a new frontier in 3D content creation thanks to the recent advances in text-to-image models. Existing methods primarily adopt a combination of pretrained depth-aware diffusion and inpainting models, yet they exhibit shortcomings such as 3D inconsistency and limited controllability. To address these challenges, we introduce InteX, a novel framework for interactive text-to-texture synthesis. 1) InteX includes a user-friendly interface that facilitates interaction and control throughout the synthesis process, enabling region-specific repainting and precise texture editing. 2) Additionally, we develop a unified depth-aware inpainting model that integrates depth information with inpainting cues, effectively mitigating 3D inconsistencies and improving generation speed. Through extensive experiments, our framework has proven to be both practical and effective in text-to-texture synthesis, paving the way for high-quality 3D content creation.

Jiaxiang Tang, Ruijie Lu, Zhaoshuo Li et al.

Recent progress in 3D object generation has greatly improved both the quality and efficiency. However, most existing methods generate a single mesh with all parts fused together, which limits the ability to edit or manipulate individual parts. A key challenge is that different objects may have a varying number of parts. To address this, we propose a new end-to-end framework for part-level 3D object generation. Given a single input image, our method generates high-quality 3D objects with an arbitrary number of complete and semantically meaningful parts. We introduce a dual volume packing strategy that organizes all parts into two complementary volumes, allowing for the creation of complete and interleaved parts that assemble into the final object. Experiments show that our model achieves better quality, diversity, and generalization than previous image-based part-level generation methods.

Ruijie Lu, Yixin Chen, Junfeng Ni et al.

Repurposing pre-trained diffusion models has been proven to be effective for NVS. However, these methods are mostly limited to a single object; directly applying such methods to compositional multi-object scenarios yields inferior results, especially incorrect object placement and inconsistent shape and appearance under novel views. How to enhance and systematically evaluate the cross-view consistency of such models remains under-explored. To address this issue, we propose MOVIS to enhance the structural awareness of the view-conditioned diffusion model for multi-object NVS in terms of model inputs, auxiliary tasks, and training strategy. First, we inject structure-aware features, including depth and object mask, into the denoising U-Net to enhance the model's comprehension of object instances and their spatial relationships. Second, we introduce an auxiliary task requiring the model to simultaneously predict novel view object masks, further improving the model's capability in differentiating and placing objects. Finally, we conduct an in-depth analysis of the diffusion sampling process and carefully devise a structure-guided timestep sampling scheduler during training, which balances the learning of global object placement and fine-grained detail recovery. To systematically evaluate the plausibility of synthesized images, we propose to assess cross-view consistency and novel view object placement alongside existing image-level NVS metrics. Extensive experiments on challenging synthetic and realistic datasets demonstrate that our method exhibits strong generalization capabilities and produces consistent novel view synthesis, highlighting its potential to guide future 3D-aware multi-object NVS tasks. Our project page is available at https://jason-aplp.github.io/MOVIS/.

Diwen Wan, Yuxiang Wang, Ruijie Lu et al.

While novel view synthesis for dynamic scenes has made significant progress, capturing skeleton models of objects and re-posing them remains a challenging task. To tackle this problem, in this paper, we propose a novel approach to automatically discover the associated skeleton model for dynamic objects from videos without the need for object-specific templates. Our approach utilizes 3D Gaussian Splatting and superpoints to reconstruct dynamic objects. Treating superpoints as rigid parts, we can discover the underlying skeleton model through intuitive cues and optimize it using the kinematic model. Besides, an adaptive control strategy is applied to avoid the emergence of redundant superpoints. Extensive experiments demonstrate the effectiveness and efficiency of our method in obtaining re-posable 3D objects. Not only can our approach achieve excellent visual fidelity, but it also allows for the real-time rendering of high-resolution images.

Ruijie Lu, Yu Liu, Jiaxiang Tang et al.

Generating articulated objects, such as laptops and microwaves, is a crucial yet challenging task with extensive applications in Embodied AI and AR/VR. Current image-to-3D methods primarily focus on surface geometry and texture, neglecting part decomposition and articulation modeling. Meanwhile, neural reconstruction approaches (e.g., NeRF or Gaussian Splatting) rely on dense multi-view or interaction data, limiting their scalability. In this paper, we introduce DreamArt, a novel framework for generating high-fidelity, interactable articulated assets from single-view images. DreamArt employs a three-stage pipeline: firstly, it reconstructs part-segmented and complete 3D object meshes through a combination of image-to-3D generation, mask-prompted 3D segmentation, and part amodal completion. Second, we fine-tune a video diffusion model to capture part-level articulation priors, leveraging movable part masks as prompt and amodal images to mitigate ambiguities caused by occlusion. Finally, DreamArt optimizes the articulation motion, represented by a dual quaternion, and conducts global texture refinement and repainting to ensure coherent, high-quality textures across all parts. Experimental results demonstrate that DreamArt effectively generates high-quality articulated objects, possessing accurate part shape, high appearance fidelity, and plausible articulation, thereby providing a scalable solution for articulated asset generation. Our project page is available at https://dream-art-0.github.io/DreamArt/.

Diwen Wan, Ruijie Lu, Gang Zeng

Rendering novel view images in dynamic scenes is a crucial yet challenging task. Current methods mainly utilize NeRF-based methods to represent the static scene and an additional time-variant MLP to model scene deformations, resulting in relatively low rendering quality as well as slow inference speed. To tackle these challenges, we propose a novel framework named Superpoint Gaussian Splatting (SP-GS). Specifically, our framework first employs explicit 3D Gaussians to reconstruct the scene and then clusters Gaussians with similar properties (e.g., rotation, translation, and location) into superpoints. Empowered by these superpoints, our method manages to extend 3D Gaussian splatting to dynamic scenes with only a slight increase in computational expense. Apart from achieving state-of-the-art visual quality and real-time rendering under high resolutions, the superpoint representation provides a stronger manipulation capability. Extensive experiments demonstrate the practicality and effectiveness of our approach on both synthetic and real-world datasets. Please see our project page at https://dnvtmf.github.io/SP_GS.github.io.

Qi Wang, Ruijie Lu, Xudong Xu et al.

The advancement of diffusion models has pushed the boundary of text-to-3D object generation. While it is straightforward to composite objects into a scene with reasonable geometry, it is nontrivial to texture such a scene perfectly due to style inconsistency and occlusions between objects. To tackle these problems, we propose a coarse-to-fine 3D scene texturing framework, referred to as RoomTex, to generate high-fidelity and style-consistent textures for untextured compositional scene meshes. In the coarse stage, RoomTex first unwraps the scene mesh to a panoramic depth map and leverages ControlNet to generate a room panorama, which is regarded as the coarse reference to ensure the global texture consistency. In the fine stage, based on the panoramic image and perspective depth maps, RoomTex will refine and texture every single object in the room iteratively along a series of selected camera views, until this object is completely painted. Moreover, we propose to maintain superior alignment between RGB and depth spaces via subtle edge detection methods. Extensive experiments show our method is capable of generating high-quality and diverse room textures, and more importantly, supporting interactive fine-grained texture control and flexible scene editing thanks to our inpainting-based framework and compositional mesh input. Our project page is available at https://qwang666.github.io/RoomTex/.

Jiaxiang Tang, Xiaokang Chen, Gang Zeng

Guided depth super-resolution is a practical task where a low-resolution and noisy input depth map is restored to a high-resolution version, with the help of a high-resolution RGB guide image. Existing methods usually view this task as a generalized guided filtering problem that relies on designing explicit filters and objective functions, or a dense regression problem that directly predicts the target image via deep neural networks. These methods suffer from either model capability or interpretability. Inspired by the recent progress in implicit neural representation, we propose to formulate the guided super-resolution as a neural implicit image interpolation problem, where we take the form of a general image interpolation but use a novel Joint Implicit Image Function (JIIF) representation to learn both the interpolation weights and values. JIIF represents the target image domain with spatially distributed local latent codes extracted from the input image and the guide image, and uses a graph attention mechanism to learn the interpolation weights at the same time in one unified deep implicit function. We demonstrate the effectiveness of our JIIF representation on guided depth super-resolution task, significantly outperforming state-of-the-art methods on three public benchmarks. Code can be found at \url{https://git.io/JC2sU}.

Yajie Xing, Jingbo Wang, Gang Zeng

Depth data provide geometric information that can bring progress in RGB-D scene parsing tasks. Several recent works propose RGB-D convolution operators that construct receptive fields along the depth-axis to handle 3D neighborhood relations between pixels. However, these methods pre-define depth receptive fields by hyperparameters, making them rely on parameter selection. In this paper, we propose a novel operator called malleable 2.5D convolution to learn the receptive field along the depth-axis. A malleable 2.5D convolution has one or more 2D convolution kernels. Our method assigns each pixel to one of the kernels or none of them according to their relative depth differences, and the assigning process is formulated as a differentiable form so that it can be learnt by gradient descent. The proposed operator runs on standard 2D feature maps and can be seamlessly incorporated into pre-trained CNNs. We conduct extensive experiments on two challenging RGB-D semantic segmentation dataset NYUDv2 and Cityscapes to validate the effectiveness and the generalization ability of our method.

Xiaokang Chen, Kwan-Yee Lin, Jingbo Wang et al.

Depth information has proven to be a useful cue in the semantic segmentation of RGB-D images for providing a geometric counterpart to the RGB representation. Most existing works simply assume that depth measurements are accurate and well-aligned with the RGB pixels and models the problem as a cross-modal feature fusion to obtain better feature representations to achieve more accurate segmentation. This, however, may not lead to satisfactory results as actual depth data are generally noisy, which might worsen the accuracy as the networks go deeper. In this paper, we propose a unified and efficient Cross-modality Guided Encoder to not only effectively recalibrate RGB feature responses, but also to distill accurate depth information via multiple stages and aggregate the two recalibrated representations alternatively. The key of the proposed architecture is a novel Separation-and-Aggregation Gating operation that jointly filters and recalibrates both representations before cross-modality aggregation. Meanwhile, a Bi-direction Multi-step Propagation strategy is introduced, on the one hand, to help to propagate and fuse information between the two modalities, and on the other hand, to preserve their specificity along the long-term propagation process. Besides, our proposed encoder can be easily injected into the previous encoder-decoder structures to boost their performance on RGB-D semantic segmentation. Our model outperforms state-of-the-arts consistently on both in-door and out-door challenging datasets. Code of this work is available at https://charlescxk.github.io/

Xiaokang Chen, Kwan-Yee Lin, Chen Qian et al.

The goal of the Semantic Scene Completion (SSC) task is to simultaneously predict a completed 3D voxel representation of volumetric occupancy and semantic labels of objects in the scene from a single-view observation. Since the computational cost generally increases explosively along with the growth of voxel resolution, most current state-of-the-arts have to tailor their framework into a low-resolution representation with the sacrifice of detail prediction. Thus, voxel resolution becomes one of the crucial difficulties that lead to the performance bottleneck. In this paper, we propose to devise a new geometry-based strategy to embed depth information with low-resolution voxel representation, which could still be able to encode sufficient geometric information, e.g., room layout, object's sizes and shapes, to infer the invisible areas of the scene with well structure-preserving details. To this end, we first propose a novel 3D sketch-aware feature embedding to explicitly encode geometric information effectively and efficiently. With the 3D sketch in hand, we further devise a simple yet effective semantic scene completion framework that incorporates a light-weight 3D Sketch Hallucination module to guide the inference of occupancy and the semantic labels via a semi-supervised structure prior learning strategy. We demonstrate that our proposed geometric embedding works better than the depth feature learning from habitual SSC frameworks. Our final model surpasses state-of-the-arts consistently on three public benchmarks, which only requires 3D volumes of 60 x 36 x 60 resolution for both input and output. The code and the supplementary material will be available at https://charlesCXK.github.io.

Falong Shen, Gang Zeng

This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low level image features. We formulate the underlying problem as the conditional random field that embeds local feature extraction, clique potential construction, and guided filtering within the same framework, and provide an efficient coarse-to-fine solver. At the coarse level, we combine local feature representation and context interaction using a deep convolutional network, and directly learn the interaction from high order cliques with a message passing routine, avoiding time-consuming explicit graph inference for joint probability distribution. At the fine level, we introduce a guided filtering interpretation for the mean field algorithm, and achieve accurate object boundaries with 100+ faster than classic learning methods. The two parts are connected and jointly trained in an end-to-end fashion. Experimental results on Pascal VOC 2012 dataset have shown that the proposed algorithm outperforms the state-of-the-art, and that it achieves the rank 1 performance at the time of submission, both of which prove the effectiveness of this unified framework for semantic image segmentation.

Jingdong Wang, Jing Wang, Gang Zeng et al.

In this paper, we propose a new data structure for approximate nearest neighbor search. This structure augments the neighborhood graph with a bridge graph. We propose to exploit Cartesian concatenation to produce a large set of vectors, called bridge vectors, from several small sets of subvectors. Each bridge vector is connected with a few reference vectors near to it, forming a bridge graph. Our approach finds nearest neighbors by simultaneously traversing the neighborhood graph and the bridge graph in the best-first strategy. The success of our approach stems from two factors: the exact nearest neighbor search over a large number of bridge vectors can be done quickly, and the reference vectors connected to a bridge (reference) vector near the query are also likely to be near the query. Experimental results on searching over large scale datasets (SIFT, GIST and HOG) show that our approach outperforms state-of-the-art ANN search algorithms in terms of efficiency and accuracy. The combination of our approach with the IVFADC system also shows superior performance over the BIGANN dataset of $1$ billion SIFT features compared with the best previously published result.

Jingdong Wang, Jing Wang, Gang Zeng et al.

The $k$-NN graph has played a central role in increasingly popular data-driven techniques for various learning and vision tasks; yet, finding an efficient and effective way to construct $k$-NN graphs remains a challenge, especially for large-scale high-dimensional data. In this paper, we propose a new approach to construct approximate $k$-NN graphs with emphasis in: efficiency and accuracy. We hierarchically and randomly divide the data points into subsets and build an exact neighborhood graph over each subset, achieving a base approximate neighborhood graph; we then repeat this process for several times to generate multiple neighborhood graphs, which are combined to yield a more accurate approximate neighborhood graph. Furthermore, we propose a neighborhood propagation scheme to further enhance the accuracy. We show both theoretical and empirical accuracy and efficiency of our approach to $k$-NN graph construction and demonstrate significant speed-up in dealing with large scale visual data.