Hao Zhang

Yanbin Hao, Hao Zhang, Chong-Wah Ngo et al.

Learning discriminative representation from the complex spatio-temporal dynamic space is essential for video recognition. On top of those stylized spatio-temporal computational units, further refining the learnt feature with axial contexts is demonstrated to be promising in achieving this goal. However, previous works generally focus on utilizing a single kind of contexts to calibrate entire feature channels and could hardly apply to deal with diverse video activities. The problem can be tackled by using pair-wise spatio-temporal attentions to recompute feature response with cross-axis contexts at the expense of heavy computations. In this paper, we propose an efficient feature refinement method that decomposes the feature channels into several groups and separately refines them with different axial contexts in parallel. We refer this lightweight feature calibration as group contextualization (GC). Specifically, we design a family of efficient element-wise calibrators, i.e., ECal-G/S/T/L, where their axial contexts are information dynamics aggregated from other axes either globally or locally, to contextualize feature channel groups. The GC module can be densely plugged into each residual layer of the off-the-shelf video networks. With little computational overhead, consistent improvement is observed when plugging in GC on different networks. By utilizing calibrators to embed feature with four different kinds of contexts in parallel, the learnt representation is expected to be more resilient to diverse types of activities. On videos with rich temporal variations, empirically GC can boost the performance of 2D-CNN (e.g., TSN and TSM) to a level comparable to the state-of-the-art video networks. Code is available at https://github.com/haoyanbin918/Group-Contextualization.

Jasmine Collins, Anqi Liang, Jitendra Malik et al. · berkeley

We present a neural network approach to transfer the motion from a single image of an articulated object to a rest-state (i.e., unarticulated) 3D model. Our network learns to predict the object's pose, part segmentation, and corresponding motion parameters to reproduce the articulation shown in the input image. The network is composed of three distinct branches that take a shared joint image-shape embedding and is trained end-to-end. Unlike previous methods, our approach is independent of the topology of the object and can work with objects from arbitrary categories. Our method, trained with only synthetic data, can be used to automatically animate a mesh, infer motion from real images, and transfer articulation to functionally similar but geometrically distinct 3D models at test time.

Hao Zhang, Tianyuan Dai, Yu-Wing Tai et al.

This paper presents the first significant work on directly predicting 3D face landmarks on neural radiance fields (NeRFs). Our 3D coarse-to-fine Face Landmarks NeRF (FLNeRF) model efficiently samples from a given face NeRF with individual facial features for accurate landmarks detection. Expression augmentation is applied to facial features in a fine scale to simulate large emotions range including exaggerated facial expressions (e.g., cheek blowing, wide opening mouth, eye blinking) for training FLNeRF. Qualitative and quantitative comparison with related state-of-the-art 3D facial landmark estimation methods demonstrate the efficacy of FLNeRF, which contributes to downstream tasks such as high-quality face editing and swapping with direct control using our NeRF landmarks. Code and data will be available. Github link: https://github.com/ZHANG1023/FLNeRF.

Zhiqin Chen, Qimin Chen, Hang Zhou et al.

We present an unsupervised 3D shape co-segmentation method which learns a set of deformable part templates from a shape collection. To accommodate structural variations in the collection, our network composes each shape by a selected subset of template parts which are affine-transformed. To maximize the expressive power of the part templates, we introduce a per-part deformation network to enable the modeling of diverse parts with substantial geometry variations, while imposing constraints on the deformation capacity to ensure fidelity to the originally represented parts. We also propose a training scheme to effectively overcome local minima. Architecturally, our network is a branched autoencoder, with a CNN encoder taking a voxel shape as input and producing per-part transformation matrices, latent codes, and part existence scores, and the decoder outputting point occupancies to define the reconstruction loss. Our network, coined DAE-Net for Deforming Auto-Encoder, can achieve unsupervised 3D shape co-segmentation that yields fine-grained, compact, and meaningful parts that are consistent across diverse shapes. We conduct extensive experiments on the ShapeNet Part dataset, DFAUST, and an animal subset of Objaverse to show superior performance over prior methods. Code and data are available at https://github.com/czq142857/DAE-Net.

Fenggen Yu, Yiming Qian, Francisca Gil-Ureta et al. · amazon-science

We present the first active learning tool for fine-grained 3D part labeling, a problem which challenges even the most advanced deep learning (DL) methods due to the significant structural variations among the small and intricate parts. For the same reason, the necessary data annotation effort is tremendous, motivating approaches to minimize human involvement. Our labeling tool iteratively verifies or modifies part labels predicted by a deep neural network, with human feedback continually improving the network prediction. To effectively reduce human efforts, we develop two novel features in our tool, hierarchical and symmetry-aware active labeling. Our human-in-the-loop approach, coined HAL3D, achieves 100% accuracy (barring human errors) on any test set with pre-defined hierarchical part labels, with 80% time-saving over manual effort.

Yang Zhao, Hao Zhang, Xiuyuan Hu · tsinghua

By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algorithms will generally incur one extra forward-backward propagation at each training iteration, which largely burdens the computation especially for scalable models. To this end, we propose a simple yet efficient training scheme, called Randomized Sharpness-Aware Training (RST). Optimizers in RST would perform a Bernoulli trial at each iteration to choose randomly from base algorithms (SGD) and sharpness-aware algorithms (SAM) with a probability arranged by a predefined scheduling function. Due to the mixture of base algorithms, the overall count of propagation pairs could be largely reduced. Also, we give theoretical analysis on the convergence of RST. Then, we empirically study the computation cost and effect of various types of scheduling functions, and give directions on setting appropriate scheduling functions. Further, we extend the RST to a general framework (G-RST), where we can adjust regularization degree on sharpness freely for any scheduling function. We show that G-RST can outperform SAM in most cases while saving 50\% extra computation cost.

Fenggen Yu, Qimin Chen, Maham Tanveer et al.

We present D$^2$CSG, a neural model composed of two dual and complementary network branches, with dropouts, for unsupervised learning of compact constructive solid geometry (CSG) representations of 3D CAD shapes. Our network is trained to reconstruct a 3D shape by a fixed-order assembly of quadric primitives, with both branches producing a union of primitive intersections or inverses. A key difference between D$^2$CSG and all prior neural CSG models is its dedicated residual branch to assemble the potentially complex shape complement, which is subtracted from an overall shape modeled by the cover branch. With the shape complements, our network is provably general, while the weight dropout further improves compactness of the CSG tree by removing redundant primitives. We demonstrate both quantitatively and qualitatively that D$^2$CSG produces compact CSG reconstructions with superior quality and more natural primitives than all existing alternatives, especially over complex and high-genus CAD shapes.

Maham Tanveer, Yizhi Wang, Ali Mahdavi-Amiri et al.

We introduce a novel method to automatically generate an artistic typography by stylizing one or more letter fonts to visually convey the semantics of an input word, while ensuring that the output remains readable. To address an assortment of challenges with our task at hand including conflicting goals (artistic stylization vs. legibility), lack of ground truth, and immense search space, our approach utilizes large language models to bridge texts and visual images for stylization and build an unsupervised generative model with a diffusion model backbone. Specifically, we employ the denoising generator in Latent Diffusion Model (LDM), with the key addition of a CNN-based discriminator to adapt the input style onto the input text. The discriminator uses rasterized images of a given letter/word font as real samples and output of the denoising generator as fake samples. Our model is coined DS-Fusion for discriminated and stylized diffusion. We showcase the quality and versatility of our method through numerous examples, qualitative and quantitative evaluation, as well as ablation studies. User studies comparing to strong baselines including CLIPDraw and DALL-E 2, as well as artist-crafted typographies, demonstrate strong performance of DS-Fusion.

Akshay Gadi Patil, Yiming Qian, Shan Yang et al.

The dominant majority of 3D models that appear in gaming, VR/AR, and those we use to train geometric deep learning algorithms are incomplete, since they are modeled as surface meshes and missing their interior structures. We present a learning framework to recover the shape interiors (RoSI) of existing 3D models with only their exteriors from multi-view and multi-articulation images. Given a set of RGB images that capture a target 3D object in different articulated poses, possibly from only few views, our method infers the interior planes that are observable in the input images. Our neural architecture is trained in a category-agnostic manner and it consists of a motion-aware multi-view analysis phase including pose, depth, and motion estimations, followed by interior plane detection in images and 3D space, and finally multi-view plane fusion. In addition, our method also predicts part articulations and is able to realize and even extrapolate the captured motions on the target 3D object. We evaluate our method by quantitative and qualitative comparisons to baselines and alternative solutions, as well as testing on untrained object categories and real image inputs to assess its generalization capabilities.

Yizhi Wang, Zeyu Huang, Ariel Shamir et al.

We introduce anchored radial observations (ARO), a novel shape encoding for learning implicit field representation of 3D shapes that is category-agnostic and generalizable amid significant shape variations. The main idea behind our work is to reason about shapes through partial observations from a set of viewpoints, called anchors. We develop a general and unified shape representation by employing a fixed set of anchors, via Fibonacci sampling, and designing a coordinate-based deep neural network to predict the occupancy value of a query point in space. Differently from prior neural implicit models that use global shape feature, our shape encoder operates on contextual, query-specific features. To predict point occupancy, locally observed shape information from the perspective of the anchors surrounding the input query point are encoded and aggregated through an attention module, before implicit decoding is performed. We demonstrate the quality and generality of our network, coined ARO-Net, on surface reconstruction from sparse point clouds, with tests on novel and unseen object categories, "one-shape" training, and comparisons to state-of-the-art neural and classical methods for reconstruction and tessellation.

Ruiqi Wang, Akshay Gadi Patil, Fenggen Yu et al.

We introduce the first active learning (AL) model for high-accuracy instance segmentation of moveable parts from RGB images of real indoor scenes. Specifically, our goal is to obtain fully validated segmentation results by humans while minimizing manual effort. To this end, we employ a transformer that utilizes a masked-attention mechanism to supervise the active segmentation. To enhance the network tailored to moveable parts, we introduce a coarse-to-fine AL approach which first uses an object-aware masked attention and then a pose-aware one, leveraging the hierarchical nature of the problem and a correlation between moveable parts and object poses and interaction directions. When applying our AL model to 2,000 real images, we obtain fully validated moveable part segmentations with semantic labels, by only needing to manually annotate 11.45% of the images. This translates to significant (60%) time saving over manual effort required by the best non-AL model to attain the same segmentation accuracy. At last, we contribute a dataset of 2,550 real images with annotated moveable parts, demonstrating its superior quality and diversity over the best alternatives.

Hao Zhang, Lumin Xu, Shenqi Lai et al.

Current image-based keypoint detection methods for animal (including human) bodies and faces are generally divided into full-supervised and few-shot class-agnostic approaches. The former typically relies on laborious and time-consuming manual annotations, posing considerable challenges in expanding keypoint detection to a broader range of keypoint categories and animal species. The latter, though less dependent on extensive manual input, still requires necessary support images with annotation for reference during testing. To realize zero-shot keypoint detection without any prior annotation, we introduce the Open-Vocabulary Keypoint Detection (OVKD) task, which is innovatively designed to use text prompts for identifying arbitrary keypoints across any species. In pursuit of this goal, we have developed a novel framework named Open-Vocabulary Keypoint Detection with Semantic-feature Matching (KDSM). This framework synergistically combines vision and language models, creating an interplay between language features and local keypoint visual features. KDSM enhances its capabilities by integrating Domain Distribution Matrix Matching (DDMM) and other special modules, such as the Vision-Keypoint Relational Awareness (VKRA) module, improving the framework's generalizability and overall performance.Our comprehensive experiments demonstrate that KDSM significantly outperforms the baseline in terms of performance and achieves remarkable success in the OVKD task.Impressively, our method, operating in a zero-shot fashion, still yields results comparable to state-of-the-art few-shot species class-agnostic keypoint detection methods.We will make the source code publicly accessible.

Juzhan Xu, Minglun Gong, Hao Zhang et al.

We present a novel learning framework to solve the transport-and-packing (TAP) problem in 3D. It constitutes a full solution pipeline from partial observations of input objects via RGBD sensing and recognition to final box placement, via robotic motion planning, to arrive at a compact packing in a target container. The technical core of our method is a neural network for TAP, trained via reinforcement learning (RL), to solve the NP-hard combinatorial optimization problem. Our network simultaneously selects an object to pack and determines the final packing location, based on a judicious encoding of the continuously evolving states of partially observed source objects and available spaces in the target container, using separate encoders both enabled with attention mechanisms. The encoded feature vectors are employed to compute the matching scores and feasibility masks of different pairings of box selection and available space configuration for packing strategy optimization. Extensive experiments, including ablation studies and physical packing execution by a real robot (Universal Robot UR5e), are conducted to evaluate our method in terms of its design choices, scalability, generalizability, and comparisons to baselines, including the most recent RL-based TAP solution. We also contribute the first benchmark for TAP which covers a variety of input settings and difficulty levels.

Zeyu Huang, Juzhan Xu, Sisi Dai et al.

We introduce NIFT, Neural Interaction Field and Template, a descriptive and robust interaction representation of object manipulations to facilitate imitation learning. Given a few object manipulation demos, NIFT guides the generation of the interaction imitation for a new object instance by matching the Neural Interaction Template (NIT) extracted from the demos in the target Neural Interaction Field (NIF) defined for the new object. Specifically, the NIF is a neural field that encodes the relationship between each spatial point and a given object, where the relative position is defined by a spherical distance function rather than occupancies or signed distances, which are commonly adopted by conventional neural fields but less informative. For a given demo interaction, the corresponding NIT is defined by a set of spatial points sampled in the demo NIF with associated neural features. To better capture the interaction, the points are sampled on the Interaction Bisector Surface (IBS), which consists of points that are equidistant to the two interacting objects and has been used extensively for interaction representation. With both point selection and pointwise features defined for better interaction encoding, NIT effectively guides the feature matching in the NIFs of the new object instances such that the relative poses are optimized to realize the manipulation while imitating the demo interactions. Experiments show that our NIFT solution outperforms state-of-the-art imitation learning methods for object manipulation and generalizes better to objects from new categories.

Qimin Chen, Zhiqin Chen, Vladimir G. Kim et al.

We present a 3D modeling method which enables end-users to refine or detailize 3D shapes using machine learning, expanding the capabilities of AI-assisted 3D content creation. Given a coarse voxel shape (e.g., one produced with a simple box extrusion tool or via generative modeling), a user can directly "paint" desired target styles representing compelling geometric details, from input exemplar shapes, over different regions of the coarse shape. These regions are then up-sampled into high-resolution geometries which adhere with the painted styles. To achieve such controllable and localized 3D detailization, we build on top of a Pyramid GAN by making it masking-aware. We devise novel structural losses and priors to ensure that our method preserves both desired coarse structures and fine-grained features even if the painted styles are borrowed from diverse sources, e.g., different semantic parts and even different shape categories. Through extensive experiments, we show that our ability to localize details enables novel interactive creative workflows and applications. Our experiments further demonstrate that in comparison to prior techniques built on global detailization, our method generates structure-preserving, high-resolution stylized geometries with more coherent shape details and style transitions.

Hao Zhang, Chunyan Feng, Jiahui Yang et al.

The goal of Temporal Action Localization (TAL) is to find the categories and temporal boundaries of actions in an untrimmed video. Most TAL methods rely heavily on action recognition models that are sensitive to action labels rather than temporal boundaries. More importantly, few works consider the background frames that are similar to action frames in pixels but dissimilar in semantics, which also leads to inaccurate temporal boundaries. To address the challenge above, we propose a Boundary-Aware Proposal Generation (BAPG) method with contrastive learning. Specifically, we define the above background frames as hard negative samples. Contrastive learning with hard negative mining is introduced to improve the discrimination of BAPG. BAPG is independent of the existing TAL network architecture, so it can be applied plug-and-play to mainstream TAL models. Extensive experimental results on THUMOS14 and ActivityNet-1.3 demonstrate that BAPG can significantly improve the performance of TAL.

Zihao Yan, Fubao Su, Mingyang Wang et al.

We introduce an active 3D reconstruction method which integrates visual perception, robot-object interaction, and 3D scanning to recover both the exterior and interior, i.e., unexposed, geometries of a target 3D object. Unlike other works in active vision which focus on optimizing camera viewpoints to better investigate the environment, the primary feature of our reconstruction is an analysis of the interactability of various parts of the target object and the ensuing part manipulation by a robot to enable scanning of occluded regions. As a result, an understanding of part articulations of the target object is obtained on top of complete geometry acquisition. Our method operates fully automatically by a Fetch robot with built-in RGBD sensors. It iterates between interaction analysis and interaction-driven reconstruction, scanning and reconstructing detected moveable parts one at a time, where both the articulated part detection and mesh reconstruction are carried out by neural networks. In the final step, all the remaining, non-articulated parts, including all the interior structures that had been exposed by prior part manipulations and subsequently scanned, are reconstructed to complete the acquisition. We demonstrate the performance of our method via qualitative and quantitative evaluation, ablation studies, comparisons to alternatives, as well as experiments in a real environment.

Chi Zhang, Lijuan Liu, Xiaoxue Zang et al.

Convolutional Neural Networks (CNN) have dominated the field of detection ever since the success of AlexNet in ImageNet classification [12]. With the sweeping reform of Transformers [27] in natural language processing, Carion et al. [2] introduce the Transformer-based detection method, i.e., DETR. However, due to the quadratic complexity in the self-attention mechanism in the Transformer, DETR is never able to incorporate multi-scale features as performed in existing CNN-based detectors, leading to inferior results in small object detection. To mitigate this issue and further improve performance of DETR, in this work, we investigate different methods to incorporate multi-scale features and find that a Bi-directional Feature Pyramid (BiFPN) works best with DETR in further raising the detection precision. With this discovery, we propose DETR++, a new architecture that improves detection results by 1.9% AP on MS COCO 2017, 11.5% AP on RICO icon detection, and 9.1% AP on RICO layout extraction over existing baselines.

Siming Zheng, Yujia Xue, Waleed Tahir et al.

We consider the image and video compression on resource limited platforms. An ultra low-cost image encoder, named Block Modulating Video Compression (BMVC) with an encoding complexity ${\cal O}(1)$ is proposed to be implemented on mobile platforms with low consumption of power and computation resources. We also develop two types of BMVC decoders, implemented by deep neural networks. The first BMVC decoder is based on the Plug-and-Play (PnP) algorithm, which is flexible to different compression ratios. And the second decoder is a memory efficient end-to-end convolutional neural network, which aims for real-time decoding. Extensive results on the high definition images and videos demonstrate the superior performance of the proposed codec and the robustness against bit quantization.

Zhifeng Ma, Hao Zhang, Jie Liu

The drastic variation of motion in spatial and temporal dimensions makes the video prediction task extremely challenging. Existing RNN models obtain higher performance by deepening or widening the model. They obtain the multi-scale features of the video only by stacking layers, which is inefficient and brings unbearable training costs (such as memory, FLOPs, and training time). Different from them, this paper proposes a spatiotemporal multi-scale model called MS-LSTM wholly from a multi-scale perspective. On the basis of stacked layers, MS-LSTM incorporates two additional efficient multi-scale designs to fully capture spatiotemporal context information. Concretely, we employ LSTMs with mirrored pyramid structures to construct spatial multi-scale representations and LSTMs with different convolution kernels to construct temporal multi-scale representations. We theoretically analyze the training cost and performance of MS-LSTM and its components. Detailed comparison experiments with twelve baseline models on four video datasets show that MS-LSTM has better performance but lower training costs.

Shirong Liu, Chenjia Bai, Zixian Guo et al.

Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly conservative policies that resemble the behavior policy, thus limiting their performance. We investigate this limitation and attribute it to the static nature of traditional constraints. In this paper, we propose a novel dynamic policy constraint that restricts the learned policy on the samples generated by the exponential moving average of previously learned policies. By integrating this self-constraint mechanism into off-policy methods, our method facilitates the learning of non-conservative policies while avoiding policy collapse in the offline setting. Theoretical results show that our approach results in a nearly monotonically improved reference policy. Extensive experiments on the D4RL MuJoCo domain demonstrate that our proposed method achieves state-of-the-art performance among the policy constraint methods.

Guibin Chen, Dixuan Lin, Jiangping Yang et al.

Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions. These intertwined limitations hinder realistic long-form synthesis and professional film-style generation. To address these limitations, we propose SkyReels-V2, an Infinite-length Film Generative Model, that synergizes Multi-modal Large Language Model (MLLM), Multi-stage Pretraining, Reinforcement Learning, and Diffusion Forcing Framework. Firstly, we design a comprehensive structural representation of video that combines the general descriptions by the Multi-modal LLM and the detailed shot language by sub-expert models. Aided with human annotation, we then train a unified Video Captioner, named SkyCaptioner-V1, to efficiently label the video data. Secondly, we establish progressive-resolution pretraining for the fundamental video generation, followed by a four-stage post-training enhancement: Initial concept-balanced Supervised Fine-Tuning (SFT) improves baseline quality; Motion-specific Reinforcement Learning (RL) training with human-annotated and synthetic distortion data addresses dynamic artifacts; Our diffusion forcing framework with non-decreasing noise schedules enables long-video synthesis in an efficient search space; Final high-quality SFT refines visual fidelity. All the code and models are available at https://github.com/SkyworkAI/SkyReels-V2.

Peiyuan Zhang, Yongqi Chen, Haofeng Huang et al.

Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient sparse attention that replaces full attention at \emph{both} training and inference. In VSA, a lightweight coarse stage pools tokens into tiles and identifies high-weight \emph{critical tokens}; a fine stage computes token-level attention only inside those tiles subjecting to block computing layout to ensure hard efficiency. This leads to a single differentiable kernel that trains end-to-end, requires no post-hoc profiling, and sustains 85\% of FlashAttention3 MFU. We perform a large sweep of ablation studies and scaling-law experiments by pretraining DiTs from 60M to 1.4B parameters. VSA reaches a Pareto point that cuts training FLOPS by 2.53$\times$ with no drop in diffusion loss. Retrofitting the open-source Wan-2.1 model speeds up attention time by 6$\times$ and lowers end-to-end generation time from 31s to 18s with comparable quality. These results establish trainable sparse attention as a practical alternative to full attention and a key enabler for further scaling of video diffusion models. Code will be available at https://github.com/hao-ai-lab/FastVideo.

Qian Yu, Peng-Tao Jiang, Hao Zhang et al.

In the realm of high-resolution (HR), fine-grained image segmentation, the primary challenge is balancing broad contextual awareness with the precision required for detailed object delineation, capturing intricate details and the finest edges of objects. Diffusion models, trained on vast datasets comprising billions of image-text pairs, such as SD V2.1, have revolutionized text-to-image synthesis by delivering exceptional quality, fine detail resolution, and strong contextual awareness, making them an attractive solution for high-resolution image segmentation. To this end, we propose DiffDIS, a diffusion-driven segmentation model that taps into the potential of the pre-trained U-Net within diffusion models, specifically designed for high-resolution, fine-grained object segmentation. By leveraging the robust generalization capabilities and rich, versatile image representation prior of the SD models, coupled with a task-specific stable one-step denoising approach, we significantly reduce the inference time while preserving high-fidelity, detailed generation. Additionally, we introduce an auxiliary edge generation task to not only enhance the preservation of fine details of the object boundaries, but reconcile the probabilistic nature of diffusion with the deterministic demands of segmentation. With these refined strategies in place, DiffDIS serves as a rapid object mask generation model, specifically optimized for generating detailed binary maps at high resolutions, while demonstrating impressive accuracy and swift processing. Experiments on the DIS5K dataset demonstrate the superiority of DiffDIS, achieving state-of-the-art results through a streamlined inference process. The source code will be publicly available at https://github.com/qianyu-dlut/DiffDIS.

Aditya Vora, Lily Goli, Andrea Tagliasacchi et al.

We introduce HiT, a novel hierarchical neural field representation for 3D shapes that learns general hierarchies in a coarse-to-fine manner across different shape categories in an unsupervised setting. Our key contribution is a hierarchical transformer (HiT), where each level learns parent-child relationships of the tree hierarchy using a compressed codebook. This codebook enables the network to automatically identify common substructures across potentially diverse shape categories. Unlike previous works that constrain the task to a fixed hierarchical structure (e.g., binary), we impose no such restriction, except for limiting the total number of nodes at each tree level. This flexibility allows our method to infer the hierarchical structure directly from data, over multiple shape categories, and representing more general and complex hierarchies than prior approaches. When trained at scale with a reconstruction loss, our model captures meaningful containment relationships between parent and child nodes. We demonstrate its effectiveness through an unsupervised shape segmentation task over all 55 ShapeNet categories, where our method successfully segments shapes into multiple levels of granularity.

Yilin Liu, Jiale Chen, Shanshan Pan et al.

We introduce a novel method for acquiring boundary representations (B-Reps) of 3D CAD models which involves a two-step process: it first applies a spatial partitioning, referred to as the ``split``, followed by a ``fit`` operation to derive a single primitive within each partition. Specifically, our partitioning aims to produce the classical Voronoi diagram of the set of ground-truth (GT) B-Rep primitives. In contrast to prior B-Rep constructions which were bottom-up, either via direct primitive fitting or point clustering, our Split-and-Fit approach is top-down and structure-aware, since a Voronoi partition explicitly reveals both the number of and the connections between the primitives. We design a neural network to predict the Voronoi diagram from an input point cloud or distance field via a binary classification. We show that our network, coined NVD-Net for neural Voronoi diagrams, can effectively learn Voronoi partitions for CAD models from training data and exhibits superior generalization capabilities. Extensive experiments and evaluation demonstrate that the resulting B-Reps, consisting of parametric surfaces, curves, and vertices, are more plausible than those obtained by existing alternatives, with significant improvements in reconstruction quality. Code will be released on https://github.com/yilinliu77/NVDNet.

Zhiqin Chen, Andrea Tagliasacchi, Thomas Funkhouser et al.

We introduce neural dual contouring (NDC), a new data-driven approach to mesh reconstruction based on dual contouring (DC). Like traditional DC, it produces exactly one vertex per grid cell and one quad for each grid edge intersection, a natural and efficient structure for reproducing sharp features. However, rather than computing vertex locations and edge crossings with hand-crafted functions that depend directly on difficult-to-obtain surface gradients, NDC uses a neural network to predict them. As a result, NDC can be trained to produce meshes from signed or unsigned distance fields, binary voxel grids, or point clouds (with or without normals); and it can produce open surfaces in cases where the input represents a sheet or partial surface. During experiments with five prominent datasets, we find that NDC, when trained on one of the datasets, generalizes well to the others. Furthermore, NDC provides better surface reconstruction accuracy, feature preservation, output complexity, triangle quality, and inference time in comparison to previous learned (e.g., neural marching cubes, convolutional occupancy networks) and traditional (e.g., Poisson) methods. Code and data are available at https://github.com/czq142857/NDC.

Lianmin Zheng, Zhuohan Li, Hao Zhang et al.

Alpa automates model-parallel training of large deep learning (DL) models by generating execution plans that unify data, operator, and pipeline parallelism. Existing model-parallel training systems either require users to manually create a parallelization plan or automatically generate one from a limited space of model parallelism configurations. They do not suffice to scale out complex DL models on distributed compute devices. Alpa distributes the training of large DL models by viewing parallelisms as two hierarchical levels: inter-operator and intra-operator parallelisms. Based on it, Alpa constructs a new hierarchical space for massive model-parallel execution plans. Alpa designs a number of compilation passes to automatically derive efficient parallel execution plans at each parallelism level. Alpa implements an efficient runtime to orchestrate the two-level parallel execution on distributed compute devices. Our evaluation shows Alpa generates parallelization plans that match or outperform hand-tuned model-parallel training systems even on models they are designed for. Unlike specialized systems, Alpa also generalizes to models with heterogeneous architectures and models without manually-designed plans. Alpa's source code is publicly available at https://github.com/alpa-projects/alpa

Qimin Chen, Johannes Merz, Aditya Sanghi et al.

We introduce UNIST, the first deep neural implicit model for general-purpose, unpaired shape-to-shape translation, in both 2D and 3D domains. Our model is built on autoencoding implicit fields, rather than point clouds which represents the state of the art. Furthermore, our translation network is trained to perform the task over a latent grid representation which combines the merits of both latent-space processing and position awareness, to not only enable drastic shape transforms but also well preserve spatial features and fine local details for natural shape translations. With the same network architecture and only dictated by the input domain pairs, our model can learn both style-preserving content alteration and content-preserving style transfer. We demonstrate the generality and quality of the translation results, and compare them to well-known baselines. Code is available at https://qiminchen.github.io/unist/.

Hao Zhang, Yanbin Hao, Chong-Wah Ngo

Transformer achieves remarkable successes in understanding 1 and 2-dimensional signals (e.g., NLP and Image Content Understanding). As a potential alternative to convolutional neural networks, it shares merits of strong interpretability, high discriminative power on hyper-scale data, and flexibility in processing varying length inputs. However, its encoders naturally contain computational intensive operations such as pair-wise self-attention, incurring heavy computational burden when being applied on the complex 3-dimensional video signals. This paper presents Token Shift Module (i.e., TokShift), a novel, zero-parameter, zero-FLOPs operator, for modeling temporal relations within each transformer encoder. Specifically, the TokShift barely temporally shifts partial [Class] token features back-and-forth across adjacent frames. Then, we densely plug the module into each encoder of a plain 2D vision transformer for learning 3D video representation. It is worth noticing that our TokShift transformer is a pure convolutional-free video transformer pilot with computational efficiency for video understanding. Experiments on standard benchmarks verify its robustness, effectiveness, and efficiency. Particularly, with input clips of 8/12 frames, the TokShift transformer achieves SOTA precision: 79.83%/80.40% on the Kinetics-400, 66.56% on EGTEA-Gaze+, and 96.80% on UCF-101 datasets, comparable or better than existing SOTA convolutional counterparts. Our code is open-sourced in: https://github.com/VideoNetworks/TokShift-Transformer.

Zhiqin Chen, Andrea Tagliasacchi, Hao Zhang

Polygonal meshes are ubiquitous, but have only played a relatively minor role in the deep learning revolution. State-of-the-art neural generative models for 3D shapes learn implicit functions and generate meshes via expensive iso-surfacing. We overcome these challenges by employing a classical spatial data structure from computer graphics, Binary Space Partitioning (BSP), to facilitate 3D learning. The core operation of BSP involves recursive subdivision of 3D space to obtain convex sets. By exploiting this property, we devise BSP-Net, a network that learns to represent a 3D shape via convex decomposition without supervision. The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built over a set of planes, where the planes and convexes are both defined by learned network weights. BSP-Net directly outputs polygonal meshes from the inferred convexes. The generated meshes are watertight, compact (i.e., low-poly), and well suited to represent sharp geometry. We show that the reconstruction quality by BSP-Net is competitive with those from state-of-the-art methods while using much fewer primitives. We also explore variations to BSP-Net including using a more generic decoder for reconstruction, more general primitives than planes, as well as training a generative model with variational auto-encoders. Code is available at https://github.com/czq142857/BSP-NET-original.

Fuxiang Tan, YuTing Kong, Yingying Fan et al.

Rain streaks degrade the image quality and seriously affect the performance of subsequent computer vision tasks, such as autonomous driving, social security, etc. Therefore, removing rain streaks from a given rainy images is of great significance. Convolutional neural networks(CNN) have been widely used in image deraining tasks, however, the local computational characteristics of convolutional operations limit the development of image deraining tasks. Recently, the popular transformer has global computational features that can further facilitate the development of image deraining tasks. In this paper, we introduce Swin-transformer into the field of image deraining for the first time to study the performance and potential of Swin-transformer in the field of image deraining. Specifically, we improve the basic module of Swin-transformer and design a three-branch model to implement single-image rain removal. The former implements the basic rain pattern feature extraction, while the latter fuses different features to further extract and process the image features. In addition, we employ a jump connection to fuse deep features and shallow features. In terms of experiments, the existing public dataset suffers from image duplication and relatively homogeneous background. So we propose a new dataset Rain3000 to validate our model. Therefore, we propose a new dataset Rain3000 for validating our model. Experimental results on the publicly available datasets Rain100L, Rain100H and our dataset Rain3000 show that our proposed method has performance and inference speed advantages over the current mainstream single-image rain streaks removal models.The source code will be available at https://github.com/H-tfx/SDNet.

Yiming Qian, Hao Zhang, Yasutaka Furukawa

This paper presents Roof-GAN, a novel generative adversarial network that generates structured geometry of residential roof structures as a set of roof primitives and their relationships. Given the number of primitives, the generator produces a structured roof model as a graph, which consists of 1) primitive geometry as raster images at each node, encoding facet segmentation and angles; 2) inter-primitive colinear/coplanar relationships at each edge; and 3) primitive geometry in a vector format at each node, generated by a novel differentiable vectorizer while enforcing the relationships. The discriminator is trained to assess the primitive raster geometry, the primitive relationships, and the primitive vector geometry in a fully end-to-end architecture. Qualitative and quantitative evaluations demonstrate the effectiveness of our approach in generating diverse and realistic roof models over the competing methods with a novel metric proposed in this paper for the task of structured geometry generation. Code and data are available at https://github.com/yi-ming-qian/roofgan .

Zhiqin Chen, Vladimir G. Kim, Matthew Fisher et al.

We introduce a deep generative network for 3D shape detailization, akin to stylization with the style being geometric details. We address the challenge of creating large varieties of high-resolution and detailed 3D geometry from a small set of exemplars by treating the problem as that of geometric detail transfer. Given a low-resolution coarse voxel shape, our network refines it, via voxel upsampling, into a higher-resolution shape enriched with geometric details. The output shape preserves the overall structure (or content) of the input, while its detail generation is conditioned on an input "style code" corresponding to a detailed exemplar. Our 3D detailization via conditional refinement is realized by a generative adversarial network, coined DECOR-GAN. The network utilizes a 3D CNN generator for upsampling coarse voxels and a 3D PatchGAN discriminator to enforce local patches of the generated model to be similar to those in the training detailed shapes. During testing, a style code is fed into the generator to condition the refinement. We demonstrate that our method can refine a coarse shape into a variety of detailed shapes with different styles. The generated results are evaluated in terms of content preservation, plausibility, and diversity. Comprehensive ablation studies are conducted to validate our network designs. Code is available at https://github.com/czq142857/DECOR-GAN.

Zhiqin Chen, Andrea Tagliasacchi, Hao Zhang

Polygonal meshes are ubiquitous in the digital 3D domain, yet they have only played a minor role in the deep learning revolution. Leading methods for learning generative models of shapes rely on implicit functions, and generate meshes only after expensive iso-surfacing routines. To overcome these challenges, we are inspired by a classical spatial data structure from computer graphics, Binary Space Partitioning (BSP), to facilitate 3D learning. The core ingredient of BSP is an operation for recursive subdivision of space to obtain convex sets. By exploiting this property, we devise BSP-Net, a network that learns to represent a 3D shape via convex decomposition. Importantly, BSP-Net is unsupervised since no convex shape decompositions are needed for training. The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built on a set of planes. The convexes inferred by BSP-Net can be easily extracted to form a polygon mesh, without any need for iso-surfacing. The generated meshes are compact (i.e., low-poly) and well suited to represent sharp geometry; they are guaranteed to be watertight and can be easily parameterized. We also show that the reconstruction quality by BSP-Net is competitive with state-of-the-art methods while using much fewer primitives. Code is available at https://github.com/czq142857/BSP-NET-original.

Zhiqin Chen, Kangxue Yin, Matthew Fisher et al.

We treat shape co-segmentation as a representation learning problem and introduce BAE-NET, a branched autoencoder network, for the task. The unsupervised BAE-NET is trained with a collection of un-segmented shapes, using a shape reconstruction loss, without any ground-truth labels. Specifically, the network takes an input shape and encodes it using a convolutional neural network, whereas the decoder concatenates the resulting feature code with a point coordinate and outputs a value indicating whether the point is inside/outside the shape. Importantly, the decoder is branched: each branch learns a compact representation for one commonly recurring part of the shape collection, e.g., airplane wings. By complementing the shape reconstruction loss with a label loss, BAE-NET is easily tuned for one-shot learning. We show unsupervised, weakly supervised, and one-shot learning results by BAE-NET, demonstrating that using only a couple of exemplars, our network can generally outperform state-of-the-art supervised methods trained on hundreds of segmented shapes. Code is available at https://github.com/czq142857/BAE-NET.

Zhiqin Chen, Hao Zhang

We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called IM-NET, for shape generation, aimed at improving the visual quality of the generated shapes. An implicit field assigns a value to each point in 3D space, so that a shape can be extracted as an iso-surface. IM-NET is trained to perform this assignment by means of a binary classifier. Specifically, it takes a point coordinate, along with a feature vector encoding a shape, and outputs a value which indicates whether the point is outside the shape or not. By replacing conventional decoders by our implicit decoder for representation learning (via IM-AE) and shape generation (via IM-GAN), we demonstrate superior results for tasks such as generative shape modeling, interpolation, and single-view 3D reconstruction, particularly in terms of visual quality. Code and supplementary material are available at https://github.com/czq142857/implicit-decoder.

Nadav Schor, Oren Katzir, Hao Zhang et al.

Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks. A reoccurring challenge is how to enable a model to generate a rich variety of samples from the entire target distribution, rather than only from a distribution confined to the training data. In other words, we would like the generative model to go beyond the observed samples and learn to generate ``unseen'', yet still plausible, data. In our work, we present CompoNet, a generative neural network for 2D or 3D shapes that is based on a part-based prior, where the key idea is for the network to synthesize shapes by varying both the shape parts and their compositions. Treating a shape not as an unstructured whole, but as a (re-)composable set of deformable parts, adds a combinatorial dimension to the generative process to enrich the diversity of the output, encouraging the generator to venture more into the ``unseen''. We show that our part-based model generates richer variety of plausible shapes compared with baseline generative models. To this end, we introduce two quantitative metrics to evaluate the diversity of a generative model and assess how well the generated data covers both the training data and unseen data from the same target distribution. Code is available at https://github.com/nschor/CompoNet.

Changqing Zou, Qian Yu, Ruofei Du et al.

We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level. The dataset is created through a novel and carefully designed crowdsourcing pipeline, enabling users to efficiently generate large quantities of realistic and diverse scene sketches. SketchyScene contains more than 29,000 scene-level sketches, 7,000+ pairs of scene templates and photos, and 11,000+ object sketches. All objects in the scene sketches have ground-truth semantic and instance masks. The dataset is also highly scalable and extensible, easily allowing augmenting and/or changing scene composition. We demonstrate the potential impact of SketchyScene by training new computational models for semantic segmentation of scene sketches and showing how the new dataset enables several applications including image retrieval, sketch colorization, editing, and captioning, etc. The dataset and code can be found at https://github.com/SketchyScene/SketchyScene.

Zili Yi, Zhiqin Chen, Hao Cai et al.

We introduce BSD-GAN, a novel multi-branch and scale-disentangled training method which enables unconditional Generative Adversarial Networks (GANs) to learn image representations at multiple scales, benefiting a wide range of generation and editing tasks. The key feature of BSD-GAN is that it is trained in multiple branches, progressively covering both the breadth and depth of the network, as resolutions of the training images increase to reveal finer-scale features. Specifically, each noise vector, as input to the generator network of BSD-GAN, is deliberately split into several sub-vectors, each corresponding to, and is trained to learn, image representations at a particular scale. During training, we progressively "de-freeze" the sub-vectors, one at a time, as a new set of higher-resolution images is employed for training and more network layers are added. A consequence of such an explicit sub-vector designation is that we can directly manipulate and even combine latent (sub-vector) codes which model different feature scales.Extensive experiments demonstrate the effectiveness of our training method in scale-disentangled learning of image representations and synthesis of novel image contents, without any extra labels and without compromising quality of the synthesized high-resolution images. We further demonstrate several image generation and manipulation applications enabled or improved by BSD-GAN. Source codes are available at https://github.com/duxingren14/BSD-GAN.

Fenggen Yu, Yiming Qian, Xu Zhang et al.

We present a differentiable rendering framework to learn structured 3D abstractions in the form of primitive assemblies from sparse RGB images capturing a 3D object. By leveraging differentiable volume rendering, our method does not require 3D supervision. Architecturally, our network follows the general pipeline of an image-conditioned neural radiance field (NeRF) exemplified by pixelNeRF for color prediction. As our core contribution, we introduce differential primitive assembly (DPA) into NeRF to output a 3D occupancy field in place of density prediction, where the predicted occupancies serve as opacity values for volume rendering. Our network, coined DPA-Net, produces a union of convexes, each as an intersection of convex quadric primitives, to approximate the target 3D object, subject to an abstraction loss and a masking loss, both defined in the image space upon volume rendering. With test-time adaptation and additional sampling and loss designs aimed at improving the accuracy and compactness of the obtained assemblies, our method demonstrates superior performance over state-of-the-art alternatives for 3D primitive abstraction from sparse views.

Hao Zhang, Fang Li, Samyak Rawlekar et al.

Reconstructing dynamic articulated objects from a singular monocular video is challenging, requiring joint estimation of shape, motion, and camera parameters from limited views. Current methods typically demand extensive computational resources and training time, and require additional human annotations such as predefined parametric models, camera poses, and key points, limiting their generalizability. We propose Synergistic Shape and Skeleton Optimization (S3O), a novel two-phase method that forgoes these prerequisites and efficiently learns parametric models including visible shapes and underlying skeletons. Conventional strategies typically learn all parameters simultaneously, leading to interdependencies where a single incorrect prediction can result in significant errors. In contrast, S3O adopts a phased approach: it first focuses on learning coarse parametric models, then progresses to motion learning and detail addition. This method substantially lowers computational complexity and enhances robustness in reconstruction from limited viewpoints, all without requiring additional annotations. To address the current inadequacies in 3D reconstruction from monocular video benchmarks, we collected the PlanetZoo dataset. Our experimental evaluations on standard benchmarks and the PlanetZoo dataset affirm that S3O provides more accurate 3D reconstruction, and plausible skeletons, and reduces the training time by approximately 60% compared to the state-of-the-art, thus advancing the state of the art in dynamic object reconstruction.

Zhewei Yao, Guoheng Sun, Lukasz Borchmann et al.

Translating natural language into SQL (Test2SQL) is a longstanding challenge at the intersection of natural language understanding and structured data access. While large language models (LLMs) have significantly improved fluency in SQL generation, producing correct and executable SQL--particularly for complex queries--remains a bottleneck. We present Arctic-Text2SQL-R1, a reinforcement learning (RL) framework and model family designed to generate accurate, executable SQL using a lightweight reward signal based solely on execution correctness. Our approach avoids brittle intermediate supervision and complex reward shaping, promoting stable training and alignment with the end task. Combined with carefully curated data, strong supervised initialization, and effective training practices, Arctic-Text2SQL-R1 achieves state-of-the-art execution accuracy across six diverse Test2SQL benchmarks, including the top position on the BIRD leaderboard. Notably, our 7B model outperforms prior 70B-class systems, highlighting the framework's scalability and efficiency. We further demonstrate inference-time robustness through simple extensions like value retrieval and majority voting. Extensive experiments and ablation studies offer both positive and negative insights, providing practical guidance for future Test2SQL research.

Jingyu Hu, Ka-Hei Hui, Zhengzhe Liu et al.

This paper introduces a new approach based on a coupled representation and a neural volume optimization to implicitly perform 3D shape editing in latent space. This work has three innovations. First, we design the coupled neural shape (CNS) representation for supporting 3D shape editing. This representation includes a latent code, which captures high-level global semantics of the shape, and a 3D neural feature volume, which provides a spatial context to associate with the local shape changes given by the editing. Second, we formulate the coupled neural shape optimization procedure to co-optimize the two coupled components in the representation subject to the editing operation. Last, we offer various 3D shape editing operators, i.e., copy, resize, delete, and drag, and derive each into an objective for guiding the CNS optimization, such that we can iteratively co-optimize the latent code and neural feature volume to match the editing target. With our approach, we can achieve a rich variety of editing results that are not only aware of the shape semantics but are also not easy to achieve by existing approaches. Both quantitative and qualitative evaluations demonstrate the strong capabilities of our approach over the state-of-the-art solutions.

Maham Tanveer, Yizhi Wang, Ruiqi Wang et al.

We present AnaMoDiff, a novel diffusion-based method for 2D motion analogies that is applied to raw, unannotated videos of articulated characters. Our goal is to accurately transfer motions from a 2D driving video onto a source character, with its identity, in terms of appearance and natural movement, well preserved, even when there may be significant discrepancies between the source and driving characters in their part proportions and movement speed and styles. Our diffusion model transfers the input motion via a latent optical flow (LOF) network operating in a noised latent space, which is spatially aware, efficient to process compared to the original RGB videos, and artifact-resistant through the diffusion denoising process even amid dense movements. To accomplish both motion analogy and identity preservation, we train our denoising model in a feature-disentangled manner, operating at two noise levels. While identity-revealing features of the source are learned via conventional noise injection, motion features are learned from LOF-warped videos by only injecting noise with large values, with the stipulation that motion properties involving pose and limbs are encoded by higher-level features. Experiments demonstrate that our method achieves the best trade-off between motion analogy and identity preservation.

Xiuyuan Hu, Guoqing Liu, Can Chen et al. · tsinghua

Structure-based drug design (SBDD) is a critical task in drug discovery, requiring the generation of molecular information across two distinct modalities: discrete molecular graphs and continuous 3D coordinates. However, existing SBDD methods often overlook two key challenges: (1) the multi-modal nature of this task and (2) the causal relationship between these modalities, limiting their plausibility and performance. To address both challenges, we propose TransDiffSBDD, an integrated framework combining autoregressive transformers and diffusion models for SBDD. Specifically, the autoregressive transformer models discrete molecular information, while the diffusion model samples continuous distributions, effectively resolving the first challenge. To address the second challenge, we design a hybrid-modal sequence for protein-ligand complexes that explicitly respects the causality between modalities. Experiments on the CrossDocked2020 benchmark demonstrate that TransDiffSBDD outperforms existing baselines.

Hao Zhang, Zhan Zhuang, Xuehao Wang et al.

Human Activity Recognition (HAR) with wearable sensors is challenged by limited interpretability, which significantly impacts cross-dataset generalization. To address this challenge, we propose Motion-Primitive Transformer (MoPFormer), a novel self-supervised framework that enhances interpretability by tokenizing inertial measurement unit signals into semantically meaningful motion primitives and leverages a Transformer architecture to learn rich temporal representations. MoPFormer comprises two stages. The first stage is to partition multi-channel sensor streams into short segments and quantize them into discrete ``motion primitive'' codewords, while the second stage enriches those tokenized sequences through a context-aware embedding module and then processes them with a Transformer encoder. The proposed MoPFormer can be pre-trained using a masked motion-modeling objective that reconstructs missing primitives, enabling it to develop robust representations across diverse sensor configurations. Experiments on six HAR benchmarks demonstrate that MoPFormer not only outperforms state-of-the-art methods but also successfully generalizes across multiple datasets. More importantly, the learned motion primitives significantly enhance both interpretability and cross-dataset performance by capturing fundamental movement patterns that remain consistent across similar activities, regardless of dataset origin.

Hao Zhang, Yu-Wing Tai, Chi-Keung Tang

The success of the GAN-NeRF structure has enabled face editing on NeRF to maintain 3D view consistency. However, achieving simultaneously multi-view consistency and temporal coherence while editing video sequences remains a formidable challenge. This paper proposes a novel face video editing architecture built upon the dynamic face GAN-NeRF structure, which effectively utilizes video sequences to restore the latent code and 3D face geometry. By editing the latent code, multi-view consistent editing on the face can be ensured, as validated by multiview stereo reconstruction on the resulting edited images in our dynamic NeRF. As the estimation of face geometries occurs on a frame-by-frame basis, this may introduce a jittering issue. We propose a stabilizer that maintains temporal coherence by preserving smooth changes of face expressions in consecutive frames. Quantitative and qualitative analyses reveal that our method, as the pioneering 4D face video editor, achieves state-of-the-art performance in comparison to existing 2D or 3D-based approaches independently addressing identity and motion. Codes will be released.

Qirui Huang, Runze Zhang, Kangjun Liu et al.

We introduce ArcPro, a novel learning framework built on architectural programs to recover structured 3D abstractions from highly sparse and low-quality point clouds. Specifically, we design a domain-specific language (DSL) to hierarchically represent building structures as a program, which can be efficiently converted into a mesh. We bridge feedforward and inverse procedural modeling by using a feedforward process for training data synthesis, allowing the network to make reverse predictions. We train an encoder-decoder on the points-program pairs to establish a mapping from unstructured point clouds to architectural programs, where a 3D convolutional encoder extracts point cloud features and a transformer decoder autoregressively predicts the programs in a tokenized form. Inference by our method is highly efficient and produces plausible and faithful 3D abstractions. Comprehensive experiments demonstrate that ArcPro outperforms both traditional architectural proxy reconstruction and learning-based abstraction methods. We further explore its potential to work with multi-view image and natural language inputs.

Yizhi Wang, Mingrui Zhao, Hao Zhang

We introduce the simple idea of adaptive view planning to multi-view synthesis, aiming to improve both occlusion revelation and 3D consistency for single-view 3D reconstruction. Instead of producing an unordered set of views independently or simultaneously, we generate a sequence of views, leveraging temporal consistency to enhance 3D coherence. More importantly, our view sequence is not determined by a pre-determined and fixed camera setup. Instead, we compute an adaptive camera trajectory (ACT), forming an orbit, which seeks to maximize the visibility of occluded regions of the 3D object to be reconstructed. Once the best orbit is found, we feed it to a video diffusion model to generate novel views around the orbit, which can then be passed to any multi-view 3D reconstruction model to obtain the final result. Our multi-view synthesis pipeline is quite efficient since it involves no run-time training/optimization, only forward inferences by applying pre-trained models for occlusion analysis and multi-view synthesis. Our method predicts camera trajectories that reveal occlusions effectively and produce consistent novel views, significantly improving 3D reconstruction over SOTA alternatives on the unseen GSO dataset. Project Page: https://mingrui-zhao.github.io/ACT-R/