Chaoyang Wang

Chaoyang Wang, Lachlan Ewen MacDonald, Laszlo A. Jeni et al.

In this paper we present a new method for deformable NeRF that can directly use optical flow as supervision. We overcome the major challenge with respect to the computationally inefficiency of enforcing the flow constraints to the backward deformation field, used by deformable NeRFs. Specifically, we show that inverting the backward deformation function is actually not needed for computing scene flows between frames. This insight dramatically simplifies the problem, as one is no longer constrained to deformation functions that can be analytically inverted. Instead, thanks to the weak assumptions required by our derivation based on the inverse function theorem, our approach can be extended to a broad class of commonly used backward deformation field. We present results on monocular novel view synthesis with rapid object motion, and demonstrate significant improvements over baselines without flow supervision.

Antanas Kascenas, Pedro Sanchez, Patrick Schrempf et al.

Pathological brain lesions exhibit diverse appearance in brain images, in terms of intensity, texture, shape, size, and location. Comprehensive sets of data and annotations are difficult to acquire. Therefore, unsupervised anomaly detection approaches have been proposed using only normal data for training, with the aim of detecting outlier anomalous voxels at test time. Denoising methods, for instance classical denoising autoencoders (DAEs) and more recently emerging diffusion models, are a promising approach, however naive application of pixelwise noise leads to poor anomaly detection performance. We show that optimization of the spatial resolution and magnitude of the noise improves the performance of different model training regimes, with similar noise parameter adjustments giving good performance for both DAEs and diffusion models. Visual inspection of the reconstructions suggests that the training noise influences the trade-off between the extent of the detail that is reconstructed and the extent of erasure of anomalies, both of which contribute to better anomaly detection performance. We validate our findings on two real-world datasets (tumor detection in brain MRI and hemorrhage/ischemia/tumor detection in brain CT), showing good detection on diverse anomaly appearances. Overall, we find that a DAE trained with coarse noise is a fast and simple method that gives state-of-the-art accuracy. Diffusion models applied to anomaly detection are as yet in their infancy and provide a promising avenue for further research.

Aarush Gupta, Junli Cao, Chaoyang Wang et al.

Real-time novel-view image synthesis on mobile devices is prohibitive due to the limited computational power and storage. Using volumetric rendering methods, such as NeRF and its derivatives, on mobile devices is not suitable due to the high computational cost of volumetric rendering. On the other hand, recent advances in neural light field representations have shown promising real-time view synthesis results on mobile devices. Neural light field methods learn a direct mapping from a ray representation to the pixel color. The current choice of ray representation is either stratified ray sampling or Plucker coordinates, overlooking the classic light slab (two-plane) representation, the preferred representation to interpolate between light field views. In this work, we find that using the light slab representation is an efficient representation for learning a neural light field. More importantly, it is a lower-dimensional ray representation enabling us to learn the 4D ray space using feature grids which are significantly faster to train and render. Although mostly designed for frontal views, we show that the light-slab representation can be further extended to non-frontal scenes using a divide-and-conquer strategy. Our method offers superior rendering quality compared to previous light field methods and achieves a significantly improved trade-off between rendering quality and speed.

Evangelos Ntavelis, Aliaksandr Siarohin, Kyle Olszewski et al. · eth-zurich

We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space, which can then be decoded into a volumetric representation for rendering view-consistent appearance and geometry. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations to learn a 3D diffusion from 2D images or monocular videos of rigid or articulated objects. Our approach is flexible enough to use either existing camera supervision or no camera information at all -- instead efficiently learning it during training. Our evaluations demonstrate that our generation results outperform state-of-the-art alternatives on various benchmark datasets and metrics, including multi-view image datasets of synthetic objects, real in-the-wild videos of moving people, and a large-scale, real video dataset of static objects.

Mosam Dabhi, Chaoyang Wang, Tim Clifford et al.

Labeling articulated objects in unconstrained settings have a wide variety of applications including entertainment, neuroscience, psychology, ethology, and many fields of medicine. Large offline labeled datasets do not exist for all but the most common articulated object categories (e.g., humans). Hand labeling these landmarks within a video sequence is a laborious task. Learned landmark detectors can help, but can be error-prone when trained from only a few examples. Multi-camera systems that train fine-grained detectors have shown significant promise in detecting such errors, allowing for self-supervised solutions that only need a small percentage of the video sequence to be hand-labeled. The approach, however, is based on calibrated cameras and rigid geometry, making it expensive, difficult to manage, and impractical in real-world scenarios. In this paper, we address these bottlenecks by combining a non-rigid 3D neural prior with deep flow to obtain high-fidelity landmark estimates from videos with only two or three uncalibrated, handheld cameras. With just a few annotations (representing 1-2% of the frames), we are able to produce 2D results comparable to state-of-the-art fully supervised methods, along with 3D reconstructions that are impossible with other existing approaches. Our Multi-view Bootstrapping in the Wild (MBW) approach demonstrates impressive results on standard human datasets, as well as tigers, cheetahs, fish, colobus monkeys, chimpanzees, and flamingos from videos captured casually in a zoo. We release the codebase for MBW as well as this challenging zoo dataset consisting image frames of tail-end distribution categories with their corresponding 2D, 3D labels generated from minimal human intervention.

Francesco Dalla Serra, Chaoyang Wang, Fani Deligianni et al.

Radiology reports are detailed text descriptions of the content of medical scans. Each report describes the presence/absence and location of relevant clinical findings, commonly including comparison with prior exams of the same patient to describe how they evolved. Radiology reporting is a time-consuming process, and scan results are often subject to delays. One strategy to speed up reporting is to integrate automated reporting systems, however clinical deployment requires high accuracy and interpretability. Previous approaches to automated radiology reporting generally do not provide the prior study as input, precluding comparison which is required for clinical accuracy in some types of scans, and offer only unreliable methods of interpretability. Therefore, leveraging an existing visual input format of anatomical tokens, we introduce two novel aspects: (1) longitudinal representation learning -- we input the prior scan as an additional input, proposing a method to align, concatenate and fuse the current and prior visual information into a joint longitudinal representation which can be provided to the multimodal report generation model; (2) sentence-anatomy dropout -- a training strategy for controllability in which the report generator model is trained to predict only sentences from the original report which correspond to the subset of anatomical regions given as input. We show through in-depth experiments on the MIMIC-CXR dataset how the proposed approach achieves state-of-the-art results while enabling anatomy-wise controllable report generation.

Zhenggang Tang, Peiye Zhuang, Chaoyang Wang et al.

The task of image-to-multi-view generation refers to generating novel views of an instance from a single image. Recent methods achieve this by extending text-to-image latent diffusion models to multi-view version, which contains an VAE image encoder and a U-Net diffusion model. Specifically, these generation methods usually fix VAE and finetune the U-Net only. However, the significant downscaling of the latent vectors computed from the input images and independent decoding leads to notable pixel-level misalignment across multiple views. To address this, we propose a novel method for pixel-level image-to-multi-view generation. Unlike prior work, we incorporate attention layers across multi-view images in the VAE decoder of a latent video diffusion model. Specifically, we introduce a depth-truncated epipolar attention, enabling the model to focus on spatially adjacent regions while remaining memory efficient. Applying depth-truncated attn is challenging during inference as the ground-truth depth is usually difficult to obtain and pre-trained depth estimation models is hard to provide accurate depth. Thus, to enhance the generalization to inaccurate depth when ground truth depth is missing, we perturb depth inputs during training. During inference, we employ a rapid multi-view to 3D reconstruction approach, NeuS, to obtain coarse depth for the depth-truncated epipolar attention. Our model enables better pixel alignment across multi-view images. Moreover, we demonstrate the efficacy of our approach in improving downstream multi-view to 3D reconstruction tasks.

Qihang Zhang, Chaoyang Wang, Aliaksandr Siarohin et al.

We are witnessing significant breakthroughs in the technology for generating 3D objects from text. Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. Generating entire scenes, however, remains very challenging as a scene contains multiple 3D objects, diverse and scattered. In this work, we introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text. We marry the locality of objects with globality of scenes by introducing a hybrid 3D representation: explicit for objects and implicit for scenes. Remarkably, an object, being represented explicitly, can be either generated from text using conventional text-to-3D approaches, or provided by users. To configure the layout of the scene and automatically place objects, we apply the Particle Swarm Optimization technique during the optimization process. Furthermore, it is difficult for certain parts of the scene (e.g., corners, occlusion) to receive multi-view supervision, leading to inferior geometry. We incorporate an RGBD panorama diffusion model to mitigate it, resulting in high-quality geometry. Extensive evaluation supports that our approach achieves superior quality over previous approaches, enabling the generation of detailed and view-consistent 3D scenes.

Tuan Duc Ngo, Peiye Zhuang, Chuang Gan et al.

Tracking dense 3D motion from monocular videos remains challenging, particularly when aiming for pixel-level precision over long sequences. We introduce DELTA, a novel method that efficiently tracks every pixel in 3D space, enabling accurate motion estimation across entire videos. Our approach leverages a joint global-local attention mechanism for reduced-resolution tracking, followed by a transformer-based upsampler to achieve high-resolution predictions. Unlike existing methods, which are limited by computational inefficiency or sparse tracking, DELTA delivers dense 3D tracking at scale, running over 8x faster than previous methods while achieving state-of-the-art accuracy. Furthermore, we explore the impact of depth representation on tracking performance and identify log-depth as the optimal choice. Extensive experiments demonstrate the superiority of DELTA on multiple benchmarks, achieving new state-of-the-art results in both 2D and 3D dense tracking tasks. Our method provides a robust solution for applications requiring fine-grained, long-term motion tracking in 3D space.

Guocheng Qian, Junli Cao, Aliaksandr Siarohin et al.

We introduce Amortized Text-to-Mesh (AToM), a feed-forward text-to-mesh framework optimized across multiple text prompts simultaneously. In contrast to existing text-to-3D methods that often entail time-consuming per-prompt optimization and commonly output representations other than polygonal meshes, AToM directly generates high-quality textured meshes in less than 1 second with around 10 times reduction in the training cost, and generalizes to unseen prompts. Our key idea is a novel triplane-based text-to-mesh architecture with a two-stage amortized optimization strategy that ensures stable training and enables scalability. Through extensive experiments on various prompt benchmarks, AToM significantly outperforms state-of-the-art amortized approaches with over 4 times higher accuracy (in DF415 dataset) and produces more distinguishable and higher-quality 3D outputs. AToM demonstrates strong generalizability, offering finegrained 3D assets for unseen interpolated prompts without further optimization during inference, unlike per-prompt solutions.

Jiraphon Yenphraphai, Ashkan Mirzaei, Jianqi Chen et al.

Video-conditioned 4D shape generation aims to recover time-varying 3D geometry and view-consistent appearance directly from an input video. In this work, we introduce a native video-to-4D shape generation framework that synthesizes a single dynamic 3D representation end-to-end from the video. Our framework introduces three key components based on large-scale pre-trained 3D models: (i) a temporal attention that conditions generation on all frames while producing a time-indexed dynamic representation; (ii) a time-aware point sampling and 4D latent anchoring that promote temporally consistent geometry and texture; and (iii) noise sharing across frames to enhance temporal stability. Our method accurately captures non-rigid motion, volume changes, and even topological transitions without per-frame optimization. Across diverse in-the-wild videos, our method improves robustness and perceptual fidelity and reduces failure modes compared with the baselines.

Tuan Duc Ngo, Ashkan Mirzaei, Guocheng Qian et al.

We propose a novel algorithm for accelerating dense long-term 3D point tracking in videos. Through analysis of existing state-of-the-art methods, we identify two major computational bottlenecks. First, transformer-based iterative tracking becomes expensive when handling a large number of trajectories. To address this, we introduce a coarse-to-fine strategy that begins tracking with a small subset of points and progressively expands the set of tracked trajectories. The newly added trajectories are initialized using a learnable interpolation module, which is trained end-to-end alongside the tracking network. Second, we propose an optimization that significantly reduces the cost of correlation feature computation, another key bottleneck in prior methods. Together, these improvements lead to a 5-100x speedup over existing approaches while maintaining state-of-the-art tracking accuracy.

Francesco Dalla Serra, Patrick Schrempf, Chaoyang Wang et al.

We present a novel approach to Chest X-ray (CXR) Visual Question Answering (VQA), addressing both single-image image-difference questions. Single-image questions focus on abnormalities within a specific CXR ("What abnormalities are seen in image X?"), while image-difference questions compare two longitudinal CXRs acquired at different time points ("What are the differences between image X and Y?"). We further explore how the integration of radiology reports can enhance the performance of VQA models. While previous approaches have demonstrated the utility of radiology reports during the pre-training phase, we extend this idea by showing that the reports can also be leveraged as additional input to improve the VQA model's predicted answers. First, we propose a unified method that handles both types of questions and auto-regressively generates the answers. For single-image questions, the model is provided with a single CXR. For image-difference questions, the model is provided with two CXRs from the same patient, captured at different time points, enabling the model to detect and describe temporal changes. Taking inspiration from 'Chain-of-Thought reasoning', we demonstrate that performance on the CXR VQA task can be improved by grounding the answer generator module with a radiology report predicted for the same CXR. In our approach, the VQA model is divided into two steps: i) Report Generation (RG) and ii) Answer Generation (AG). Our results demonstrate that incorporating predicted radiology reports as evidence to the AG model enhances performance on both single-image and image-difference questions, achieving state-of-the-art results on the Medical-Diff-VQA dataset.

Heng Yu, Chaoyang Wang, Peiye Zhuang et al.

Existing dynamic scene generation methods mostly rely on distilling knowledge from pre-trained 3D generative models, which are typically fine-tuned on synthetic object datasets. As a result, the generated scenes are often object-centric and lack photorealism. To address these limitations, we introduce a novel pipeline designed for photorealistic text-to-4D scene generation, discarding the dependency on multi-view generative models and instead fully utilizing video generative models trained on diverse real-world datasets. Our method begins by generating a reference video using the video generation model. We then learn the canonical 3D representation of the video using a freeze-time video, delicately generated from the reference video. To handle inconsistencies in the freeze-time video, we jointly learn a per-frame deformation to model these imperfections. We then learn the temporal deformation based on the canonical representation to capture dynamic interactions in the reference video. The pipeline facilitates the generation of dynamic scenes with enhanced photorealism and structural integrity, viewable from multiple perspectives, thereby setting a new standard in 4D scene generation.

Chaoyang Wang, Xiangtai Li, Henghui Ding et al.

In-context segmentation has drawn increasing attention with the advent of vision foundation models. Its goal is to segment objects using given reference images. Most existing approaches adopt metric learning or masked image modeling to build the correlation between visual prompts and input image queries. This work approaches the problem from a fresh perspective - unlocking the capability of the latent diffusion model (LDM) for in-context segmentation and investigating different design choices. Specifically, we examine the problem from three angles: instruction extraction, output alignment, and meta-architectures. We design a two-stage masking strategy to prevent interfering information from leaking into the instructions. In addition, we propose an augmented pseudo-masking target to ensure the model predicts without forgetting the original images. Moreover, we build a new and fair in-context segmentation benchmark that covers both image and video datasets. Experiments validate the effectiveness of our approach, demonstrating comparable or even stronger results than previous specialist or visual foundation models. We hope our work inspires others to rethink the unification of segmentation and generation.

Chaoyang Wang, Ben Eckart, Simon Lucey et al.

Recent approaches to render photorealistic views from a limited set of photographs have pushed the boundaries of our interactions with pictures of static scenes. The ability to recreate moments, that is, time-varying sequences, is perhaps an even more interesting scenario, but it remains largely unsolved. We introduce DCT-NeRF, a coordinatebased neural representation for dynamic scenes. DCTNeRF learns smooth and stable trajectories over the input sequence for each point in space. This allows us to enforce consistency between any two frames in the sequence, which results in high quality reconstruction, particularly in dynamic regions.

Chen-Hsuan Lin, Chaoyang Wang, Simon Lucey

Dense 3D object reconstruction from a single image has recently witnessed remarkable advances, but supervising neural networks with ground-truth 3D shapes is impractical due to the laborious process of creating paired image-shape datasets. Recent efforts have turned to learning 3D reconstruction without 3D supervision from RGB images with annotated 2D silhouettes, dramatically reducing the cost and effort of annotation. These techniques, however, remain impractical as they still require multi-view annotations of the same object instance during training. As a result, most experimental efforts to date have been limited to synthetic datasets. In this paper, we address this issue and propose SDF-SRN, an approach that requires only a single view of objects at training time, offering greater utility for real-world scenarios. SDF-SRN learns implicit 3D shape representations to handle arbitrary shape topologies that may exist in the datasets. To this end, we derive a novel differentiable rendering formulation for learning signed distance functions (SDF) from 2D silhouettes. Our method outperforms the state of the art under challenging single-view supervision settings on both synthetic and real-world datasets.

Chaoyang Wang, Zhiqiang Guo, Guohui Li et al.

Due to the development of graph neural networks, graph-based representation learning methods have made great progress in recommender systems. However, data sparsity is still a challenging problem that most graph-based recommendation methods are confronted with. Recent works try to address this problem by utilizing side information. In this paper, we exploit the relevant and easily accessible textual information by advanced natural language processing (NLP) models and propose a light RGCN-based (RGCN, relational graph convolutional network) collaborative filtering method on heterogeneous graphs. Specifically, to incorporate rich textual knowledge, we utilize a pre-trained NLP model to initialize the embeddings of text nodes. Afterward, by performing a simplified RGCN-based node information propagation on the constructed heterogeneous graph, the embeddings of users and items can be adjusted with textual knowledge, which effectively alleviates the negative effects of data sparsity. Moreover, the matching function used by most graph-based representation learning methods is the inner product, which is not appropriate for the obtained embeddings that contain complex semantics. We design a predictive network that combines graph-based representation learning with neural matching function learning, and demonstrate that this architecture can bring a significant performance improvement. Extensive experiments are conducted on three publicly available datasets, and the results verify the superior performance of our method over several baselines.

Chaoyang Wang, Zhiqiang Guo, Jianjun Li et al.

Due to its nature of learning from dynamic interactions and planning for long-run performance, reinforcement learning (RL) recently has received much attention in interactive recommender systems (IRSs). IRSs usually face the large discrete action space problem, which makes most of the existing RL-based recommendation methods inefficient. Moreover, data sparsity is another challenging problem that most IRSs are confronted with. While the textual information like reviews and descriptions is less sensitive to sparsity, existing RL-based recommendation methods either neglect or are not suitable for incorporating textual information. To address these two problems, in this paper, we propose a Text-based Deep Deterministic Policy Gradient framework (TDDPG-Rec) for IRSs. Specifically, we leverage textual information to map items and users into a feature space, which greatly alleviates the sparsity problem. Moreover, we design an effective method to construct an action candidate set. By the policy vector dynamically learned from TDDPG-Rec that expresses the user's preference, we can select actions from the candidate set effectively. Through experiments on three public datasets, we demonstrate that TDDPG-Rec achieves state-of-the-art performance over several baselines in a time-efficient manner.

Chaoyang Wang, Chen Kong, Simon Lucey

We propose to learn a 3D pose estimator by distilling knowledge from Non-Rigid Structure from Motion (NRSfM). Our method uses solely 2D landmark annotations. No 3D data, multi-view/temporal footage, or object specific prior is required. This alleviates the data bottleneck, which is one of the major concern for supervised methods. The challenge for using NRSfM as teacher is that they often make poor depth reconstruction when the 2D projections have strong ambiguity. Directly using those wrong depth as hard target would negatively impact the student. Instead, we propose a novel loss that ties depth prediction to the cost function used in NRSfM. This gives the student pose estimator freedom to reduce depth error by associating with image features. Validated on H3.6M dataset, our learned 3D pose estimation network achieves more accurate reconstruction compared to NRSfM methods. It also outperforms other weakly supervised methods, in spite of using significantly less supervision.

Rui Zhu, Chaoyang Wang, Chen-Hsuan Lin et al.

Reconstructing 3D shapes from a sequence of images has long been a problem of interest in computer vision. Classical Structure from Motion (SfM) methods have attempted to solve this problem through projected point displacement \& bundle adjustment. More recently, deep methods have attempted to solve this problem by directly learning a relationship between geometry and appearance. There is, however, a significant gap between these two strategies. SfM tackles the problem from purely a geometric perspective, taking no account of the object shape prior. Modern deep methods more often throw away geometric constraints altogether, rendering the results unreliable. In this paper we make an effort to bring these two seemingly disparate strategies together. We introduce learned shape prior in the form of deep shape generators into Photometric Bundle Adjustment (PBA) and propose to accommodate full 3D shape generated by the shape prior within the optimization-based inference framework, demonstrating impressive results.

Chaoyang Wang, Hamed Kiani Galoogahi, Chen-Hsuan Lin et al.

In this paper we present a new approach for efficient regression based object tracking which we refer to as Deep- LK. Our approach is closely related to the Generic Object Tracking Using Regression Networks (GOTURN) framework of Held et al. We make the following contributions. First, we demonstrate that there is a theoretical relationship between siamese regression networks like GOTURN and the classical Inverse-Compositional Lucas & Kanade (IC-LK) algorithm. Further, we demonstrate that unlike GOTURN IC-LK adapts its regressor to the appearance of the currently tracked frame. We argue that this missing property in GOTURN can be attributed to its poor performance on unseen objects and/or viewpoints. Second, we propose a novel framework for object tracking - which we refer to as Deep-LK - that is inspired by the IC-LK framework. Finally, we show impressive results demonstrating that Deep-LK substantially outperforms GOTURN. Additionally, we demonstrate comparable tracking performance to current state of the art deep-trackers whilst being an order of magnitude (i.e. 100 FPS) computationally efficient.