Jia-Wang Bian

Libo Sun, Jia-Wang Bian, Huangying Zhan et al. · bytedance, oxford

Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions. Consequently, existing methods show poor accuracy in dynamic scenes, and the estimated depth map is blurred at object boundaries because they are usually occluded in other training views. In this paper, we propose SC-DepthV3 for addressing the challenges. Specifically, we introduce an external pretrained monocular depth estimation model for generating single-image depth prior, namely pseudo-depth, based on which we propose novel losses to boost self-supervised training. As a result, our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes. We demonstrate the significantly superior performance of our method over previous methods on six challenging datasets, and we provide detailed ablation studies for the proposed terms. Source code and data will be released at https://github.com/JiawangBian/sc_depth_pl

Wenjing Bian, Zirui Wang, Kejie Li et al. · bytedance, oxford

Training a Neural Radiance Field (NeRF) without pre-computed camera poses is challenging. Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes. However, these methods still face difficulties during dramatic camera movement. We tackle this challenging problem by incorporating undistorted monocular depth priors. These priors are generated by correcting scale and shift parameters during training, with which we are then able to constrain the relative poses between consecutive frames. This constraint is achieved using our proposed novel loss functions. Experiments on real-world indoor and outdoor scenes show that our method can handle challenging camera trajectories and outperforms existing methods in terms of novel view rendering quality and pose estimation accuracy. Our project page is https://nope-nerf.active.vision.

Kejie Li, Jia-Wang Bian, Robert Castle et al. · bytedance, oxford

High-quality 3D ground-truth shapes are critical for 3D object reconstruction evaluation. However, it is difficult to create a replica of an object in reality, and even 3D reconstructions generated by 3D scanners have artefacts that cause biases in evaluation. To address this issue, we introduce a novel multi-view RGBD dataset captured using a mobile device, which includes highly precise 3D ground-truth annotations for 153 object models featuring a diverse set of 3D structures. We obtain precise 3D ground-truth shape without relying on high-end 3D scanners by utilising LEGO models with known geometry as the 3D structures for image capture. The distinct data modality offered by high-resolution RGB images and low-resolution depth maps captured on a mobile device, when combined with precise 3D geometry annotations, presents a unique opportunity for future research on high-fidelity 3D reconstruction. Furthermore, we evaluate a range of 3D reconstruction algorithms on the proposed dataset. Project page: http://code.active.vision/MobileBrick/

Guangkai Xu, Wei Yin, Jianming Zhang et al.

Existing depth completion methods are often targeted at a specific sparse depth type and generalize poorly across task domains. We present a method to complete sparse/semi-dense, noisy, and potentially low-resolution depth maps obtained by various range sensors, including those in modern mobile phones, or by multi-view reconstruction algorithms. Our method leverages a data-driven prior in the form of a single image depth prediction network trained on large-scale datasets, the output of which is used as an input to our model. We propose an effective training scheme where we simulate various sparsity patterns in typical task domains. In addition, we design two new benchmarks to evaluate the generalizability and the robustness of depth completion methods. Our simple method shows superior cross-domain generalization ability against state-of-the-art depth completion methods, introducing a practical solution to high-quality depth capture on a mobile device. The code is available at: https://github.com/YvanYin/FillDepth.

Jia-Wang Bian, Wenjing Bian, Victor Adrian Prisacariu et al. · bytedance, oxford

Neural surface reconstruction is sensitive to the camera pose noise, even if state-of-the-art pose estimators like COLMAP or ARKit are used. More importantly, existing Pose-NeRF joint optimisation methods have struggled to improve pose accuracy in challenging real-world scenarios. To overcome the challenges, we introduce the pose residual field (PoRF), a novel implicit representation that uses an MLP for regressing pose updates. This is more robust than the conventional pose parameter optimisation due to parameter sharing that leverages global information over the entire sequence. Furthermore, we propose an epipolar geometry loss to enhance the supervision that leverages the correspondences exported from COLMAP results without the extra computational overhead. Our method yields promising results. On the DTU dataset, we reduce the rotation error by 78\% for COLMAP poses, leading to the decreased reconstruction Chamfer distance from 3.48mm to 0.85mm. On the MobileBrick dataset that contains casually captured unbounded 360-degree videos, our method refines ARKit poses and improves the reconstruction F1 score from 69.18 to 75.67, outperforming that with the dataset provided ground-truth pose (75.14). These achievements demonstrate the efficacy of our approach in refining camera poses and improving the accuracy of neural surface reconstruction in real-world scenarios.

Weijie Wang, Qihang Cao, Sensen Gao et al.

Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and interacting with the physical world. While traditional methods achieve high fidelity, they are limited by slow per-scene optimization or category-specific training, which hinders their practical deployment and scalability. Hence, generalizable feed-forward 3D reconstruction has witnessed rapid development in recent years. By learning a model that maps images directly to 3D representations in a single forward pass, these methods enable efficient reconstruction and robust cross-scene generalization. Our survey is motivated by a critical observation: despite the diverse geometric output representations, ranging from implicit fields to explicit primitives, existing feed-forward approaches share similar high-level architectural patterns, such as image feature extraction backbones, multi-view information fusion mechanisms, and geometry-aware design principles. Consequently, we abstract away from these representation differences and instead focus on model design, proposing a novel taxonomy centered on model design strategies that are agnostic to the output format. Our proposed taxonomy organizes the research directions into five key problems that drive recent research development: feature enhancement, geometry awareness, model efficiency, augmentation strategies and temporal-aware models. To support this taxonomy with empirical grounding and standardized evaluation, we further comprehensively review related benchmarks and datasets, and extensively discuss and categorize real-world applications based on feed-forward 3D models. Finally, we outline future directions to address open challenges such as scalability, evaluation standards, and world modeling.

Le Zhang, Qibin Hou, Yun Liu et al.

Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm. Existing deep ensemble methods usually naively train many different models and then aggregate their predictions. This is not optimal in our view from two aspects: i) Naively training multiple models adds much more computational burden, especially in the deep learning era; ii) Purely optimizing each base model without considering their interactions limits the diversity of ensemble and performance gains. We tackle these issues by proposing deep negative correlation classification (DNCC), in which the accuracy and diversity trade-off is systematically controlled by decomposing the loss function seamlessly into individual accuracy and the correlation between individual models and the ensemble. DNCC yields a deep classification ensemble where the individual estimator is both accurate and negatively correlated. Thanks to the optimized diversities, DNCC works well even when utilizing a shared network backbone, which significantly improves its efficiency when compared with most existing ensemble systems. Extensive experiments on multiple benchmark datasets and network structures demonstrate the superiority of the proposed method.

Xianzheng Ma, Brandon Smart, Yash Bhalgat et al. · bytedance, oxford

As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and interacting with physical spaces. This survey provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data. Highlighting the unique advantages of LLMs, such as in-context learning, step-by-step reasoning, open-vocabulary capabilities, and extensive world knowledge, we underscore their potential to significantly advance spatial comprehension and interaction within embodied Artificial Intelligence (AI) systems. Our investigation spans various 3D data representations, from point clouds to Neural Radiance Fields (NeRFs). It examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue, as well as LLM-based agents for spatial reasoning, planning, and navigation. The paper also includes a brief review of other methods that integrate 3D and language. The meta-analysis presented in this paper reveals significant progress yet underscores the necessity for novel approaches to harness the full potential of 3D-LLMs. Hence, with this paper, we aim to chart a course for future research that explores and expands the capabilities of 3D-LLMs in understanding and interacting with the complex 3D world. To support this survey, we have established a project page where papers related to our topic are organized and listed: https://github.com/ActiveVisionLab/Awesome-LLM-3D.

Tao Tang, Enhui Ma, xia zhou et al.

Autonomous driving has seen remarkable advancements, largely driven by extensive real-world data collection. However, acquiring diverse and corner-case data remains costly and inefficient. Generative models have emerged as a promising solution by synthesizing realistic sensor data. However, existing approaches primarily focus on single-modality generation, leading to inefficiencies and misalignment in multimodal sensor data. To address these challenges, we propose OminiGen, which generates aligned multimodal sensor data in a unified framework. Our approach leverages a shared Bird\u2019s Eye View (BEV) space to unify multimodal features and designs a novel generalizable multimodal reconstruction method, UAE, to jointly decode LiDAR and multi-view camera data. UAE achieves multimodal sensor decoding through volume rendering, enabling accurate and flexible reconstruction. Furthermore, we incorporate a Diffusion Transformer (DiT) with a ControlNet branch to enable controllable multimodal sensor generation. Our comprehensive experiments demonstrate that OminiGen achieves desired performances in unified multimodal sensor data generation with multimodal consistency and flexible sensor adjustments.

Jiawei Xu, Zhizhou Zhong, Zhijian Shu et al.

Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving relies heavily on expensive manual annotations to supervise trajectory planning, which severely limits its scalability. Conversely, although existing perception-free driving world models achieve impressive driving performance, their real-world reasoning ability for planning is solely built on next frame image forecasting. Due to the lack of enough supervision, these models often struggle with comprehensive scene understanding, resulting in unsatisfactory trajectory planning. In this paper, we propose EponaV2, a novel paradigm of driving world models, which achieves high-quality planning with comprehensive future reasoning. Inspired by how human drivers anticipate 3D geometry and semantics, we train our model to forecast more comprehensive future representations, which can be additionally decoded to future geometry and semantic maps. Extracting the 3D and semantic modalities enables our model to deeply understand the surrounding environment, and the future prediction task significantly enhances the real-world reasoning capabilities of EponaV2, ultimately leading to improved trajectory planning. Moreover, inspired by the training recipe of Large Language Models (LLMs), we introduce a flow matching group relative policy optimization mechanism to further improve planning accuracy. The state-of-the-art (SOTA) performances of EponaV2 among perception-free models on three NAVSIM benchmarks (+1.3PDMS, +5.5EPDMS) demonstrate the effectiveness of our methods.

Zihui Gao, Jia-Wang Bian, Guosheng Lin et al.

Surface reconstruction and novel view rendering from sparse-view images are challenging. Signed Distance Function (SDF)-based methods struggle with fine details, while 3D Gaussian Splatting (3DGS)-based approaches lack global geometry coherence. We propose a novel hybrid method that combines the strengths of both approaches: SDF captures coarse geometry to enhance 3DGS-based rendering, while newly rendered images from 3DGS refine the details of SDF for accurate surface reconstruction. As a result, our method surpasses state-of-the-art approaches in surface reconstruction and novel view synthesis on the DTU and MobileBrick datasets. Code will be released at https://github.com/aim-uofa/SurfaceSplat.

Kaichen Zhou, Jia-Wang Bian, Jian-Qing Zheng et al.

Despite advancements in self-supervised monocular depth estimation, challenges persist in dynamic scenarios due to the dependence on assumptions about a static world. In this paper, we present Manydepth2, to achieve precise depth estimation for both dynamic objects and static backgrounds, all while maintaining computational efficiency. To tackle the challenges posed by dynamic content, we incorporate optical flow and coarse monocular depth to create a pseudo-static reference frame. This frame is then utilized to build a motion-aware cost volume in collaboration with the vanilla target frame. Furthermore, to improve the accuracy and robustness of the network architecture, we propose an attention-based depth network that effectively integrates information from feature maps at different resolutions by incorporating both channel and non-local attention mechanisms. Compared to methods with similar computational costs, Manydepth2 achieves a significant reduction of approximately five percent in root-mean-square error for self-supervised monocular depth estimation on the KITTI-2015 dataset. The code could be found at https://github.com/kaichen-z/Manydepth2.

Huangying Zhan, Chamara Saroj Weerasekera, Jia-Wang Bian et al.

Multi-view geometry-based methods dominate the last few decades in monocular Visual Odometry for their superior performance, while they have been vulnerable to dynamic and low-texture scenes. More importantly, monocular methods suffer from scale-drift issue, i.e., errors accumulate over time. Recent studies show that deep neural networks can learn scene depths and relative camera in a self-supervised manner without acquiring ground truth labels. More surprisingly, they show that the well-trained networks enable scale-consistent predictions over long videos, while the accuracy is still inferior to traditional methods because of ignoring geometric information. Building on top of recent progress in computer vision, we design a simple yet robust VO system by integrating multi-view geometry and deep learning on Depth and optical Flow, namely DF-VO. In this work, a) we propose a method to carefully sample high-quality correspondences from deep flows and recover accurate camera poses with a geometric module; b) we address the scale-drift issue by aligning geometrically triangulated depths to the scale-consistent deep depths, where the dynamic scenes are taken into account. Comprehensive ablation studies show the effectiveness of the proposed method, and extensive evaluation results show the state-of-the-art performance of our system, e.g., Ours (1.652%) v.s. ORB-SLAM (3.247%}) in terms of translation error in KITTI Odometry benchmark. Source code is publicly available at: \href{https://github.com/Huangying-Zhan/DF-VO}{DF-VO}.

Xinyu Zhang, Xinlong Wang, Jia-Wang Bian et al.

Person search aims to localize and identify a specific person from a gallery of images. Recent methods can be categorized into two groups, i.e., two-step and end-to-end approaches. The former views person search as two independent tasks and achieves dominant results using separately trained person detection and re-identification (Re-ID) models. The latter performs person search in an end-to-end fashion. Although the end-to-end approaches yield higher inference efficiency, they largely lag behind those two-step counterparts in terms of accuracy. In this paper, we argue that the gap between the two kinds of methods is mainly caused by the Re-ID sub-networks of end-to-end methods. To this end, we propose a simple yet strong end-to-end network with diverse knowledge distillation to break the bottleneck. We also design a spatial-invariant augmentation to assist model to be invariant to inaccurate detection results. Experimental results on the CUHK-SYSU and PRW datasets demonstrate the superiority of our method against existing approaches -- it achieves on par accuracy with state-of-the-art two-step methods while maintaining high efficiency due to the single joint model. Code is available at: https://git.io/DKD-PersonSearch.

Jing Wu, Jia-Wang Bian, Xinghui Li et al. · bytedance, oxford

We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS). Our method first renders a collection of images by using the 3DGS and edits them by using a pre-trained 2D diffusion model (ControlNet) based on the input prompt, which is then used to optimise the 3D model. Our key contribution is multi-view consistent editing, which enables editing all images together instead of iteratively editing one image while updating the 3D model as in previous works. It leads to faster editing as well as higher visual quality. This is achieved by the two terms: (a) depth-conditioned editing that enforces geometric consistency across multi-view images by leveraging naturally consistent depth maps. (b) attention-based latent code alignment that unifies the appearance of edited images by conditioning their editing to several reference views through self and cross-view attention between images' latent representations. Experiments demonstrate that our method achieves faster editing and better visual results than previous state-of-the-art methods.

Zhaoqing Wang, Xiaobo Xia, Zhuolin Bie et al.

Recent advances in video diffusion models have remarkably improved camera-controlled video generation, but most methods rely solely on supervised fine-tuning (SFT), leaving online reinforcement learning (RL) post-training largely underexplored. In this work, we introduce an online RL post-training framework that optimizes a pretrained video generator for precise camera control. To make RL effective in this setting, we design a verifiable geometry reward that delivers dense segment-level feedback to guide model optimization. Specifically, we estimate the 3D camera trajectories for both generated and reference videos, divide each trajectory into short segments, and compute segment-wise relative poses. The reward function then compares each generated-reference segment pair and assigns an alignment score as the reward signal, which helps alleviate reward sparsity and improve optimization efficiency. Moreover, we construct a comprehensive dataset featuring diverse large-amplitude camera motions and scenes with varied subject dynamics. Extensive experiments show that our online RL post-training clearly outperforms SFT baselines across multiple aspects, including camera-control accuracy, geometric consistency, and visual quality, demonstrating its superiority in advancing camera-controlled video generation.

Duochao Shi, Weijie Wang, Donny Y. Chen et al. · bytedance

Depth maps are widely used in feed-forward 3D Gaussian Splatting (3DGS) pipelines by unprojecting them into 3D point clouds for novel view synthesis. This approach offers advantages such as efficient training, the use of known camera poses, and accurate geometry estimation. However, depth discontinuities at object boundaries often lead to fragmented or sparse point clouds, degrading rendering quality -- a well-known limitation of depth-based representations. To tackle this issue, we introduce PM-Loss, a novel regularization loss based on a pointmap predicted by a pre-trained transformer. Although the pointmap itself may be less accurate than the depth map, it effectively enforces geometric smoothness, especially around object boundaries. With the improved depth map, our method significantly improves the feed-forward 3DGS across various architectures and scenes, delivering consistently better rendering results. Our project page: https://aim-uofa.github.io/PMLoss

Jingyu Guo, Sensen Gao, Jia-Wang Bian et al.

Recent 3D content generation pipelines often leverage Variational Autoencoders (VAEs) to encode shapes into compact latent representations, facilitating diffusion-based generation. Efficiently compressing 3D shapes while preserving intricate geometric details remains a key challenge. Existing 3D shape VAEs often employ uniform point sampling and 1D/2D latent representations, such as vector sets or triplanes, leading to significant geometric detail loss due to inadequate surface coverage and the absence of explicit 3D representations in the latent space. Although recent work explores 3D latent representations, their large scale hinders high-resolution encoding and efficient training. Given these challenges, we introduce Hyper3D, which enhances VAE reconstruction through efficient 3D representation that integrates hybrid triplane and octree features. First, we adopt an octree-based feature representation to embed mesh information into the network, mitigating the limitations of uniform point sampling in capturing geometric distributions along the mesh surface. Furthermore, we propose a hybrid latent space representation that integrates a high-resolution triplane with a low-resolution 3D grid. This design not only compensates for the lack of explicit 3D representations but also leverages a triplane to preserve high-resolution details. Experimental results demonstrate that Hyper3D outperforms traditional representations by reconstructing 3D shapes with higher fidelity and finer details, making it well-suited for 3D generation pipelines.

Sensen Gao, Shanshan Zhao, Xu Jiang et al.

Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key limitations: the former loses structural detail, while the latter struggles with context modeling. Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, i.e., combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG. This approach enables holistic retrieval and reasoning across all modalities, unlocking comprehensive document intelligence. Recognizing its importance, this paper presents a systematic survey of Multimodal RAG for document understanding. We propose a taxonomy based on domain, retrieval modality, and granularity, and review advances involving graph structures and agentic frameworks. We also summarize key datasets, benchmarks, and applications, and highlight open challenges in efficiency, fine-grained representation, and robustness, providing a roadmap for future progress in document AI.

Tao Tang, Likui Zhang, Youpeng Wen et al.

The development of generalist robot manipulation policies has seen significant progress, driven by large-scale demonstration data across diverse environments. However, the high cost and inefficiency of collecting real-world demonstrations hinder the scalability of data acquisition. While existing simulation platforms enable controlled environments for robotic learning, the challenge of bridging the sim-to-real gap remains. To address these challenges, we propose RoboPearls, an editable video simulation framework for robotic manipulation. Built on 3D Gaussian Splatting (3DGS), RoboPearls enables the construction of photo-realistic, view-consistent simulations from demonstration videos, and supports a wide range of simulation operators, including various object manipulations, powered by advanced modules like Incremental Semantic Distillation (ISD) and 3D regularized NNFM Loss (3D-NNFM). Moreover, by incorporating large language models (LLMs), RoboPearls automates the simulation production process in a user-friendly manner through flexible command interpretation and execution. Furthermore, RoboPearls employs a vision-language model (VLM) to analyze robotic learning issues to close the simulation loop for performance enhancement. To demonstrate the effectiveness of RoboPearls, we conduct extensive experiments on multiple datasets and scenes, including RLBench, COLOSSEUM, Ego4D, Open X-Embodiment, and a real-world robot, which demonstrate our satisfactory simulation performance.

Zhengqing Gao, Dongting Hu, Jia-Wang Bian et al.

3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required, posing challenges for deployment on lightweight devices. Recent methods address this issue by compressing the storage size of densified Gaussians, yet fail to preserve rendering quality and efficiency. To overcome these limitations, we propose ProtoGS to learn Gaussian prototypes to represent Gaussian primitives, significantly reducing the total Gaussian amount without sacrificing visual quality. Our method directly uses Gaussian prototypes to enable efficient rendering and leverage the resulting reconstruction loss to guide prototype learning. To further optimize memory efficiency during training, we incorporate structure-from-motion (SfM) points as anchor points to group Gaussian primitives. Gaussian prototypes are derived within each group by clustering of K-means, and both the anchor points and the prototypes are optimized jointly. Our experiments on real-world and synthetic datasets prove that we outperform existing methods, achieving a substantial reduction in the number of Gaussians, and enabling high rendering speed while maintaining or even enhancing rendering fidelity.

Jia-Wang Bian, Huangying Zhan, Naiyan Wang et al.

We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time. Our contributions include: (i) we propose a geometry consistency loss, which penalizes the inconsistency of predicted depths between adjacent views; (ii) we propose a self-discovered mask to automatically localize moving objects that violate the underlying static scene assumption and cause noisy signals during training; (iii) we demonstrate the efficacy of each component with a detailed ablation study and show high-quality depth estimation results in both KITTI and NYUv2 datasets. Moreover, thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system for more robust and accurate tracking. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training. Finally, we provide several demos for qualitative evaluation.

Yu-Huan Wu, Yun Liu, Jun Xu et al.

The high computational cost of neural networks has prevented recent successes in RGB-D salient object detection (SOD) from benefiting real-world applications. Hence, this paper introduces a novel network, MobileSal, which focuses on efficient RGB-D SOD using mobile networks for deep feature extraction. However, mobile networks are less powerful in feature representation than cumbersome networks. To this end, we observe that the depth information of color images can strengthen the feature representation related to SOD if leveraged properly. Therefore, we propose an implicit depth restoration (IDR) technique to strengthen the mobile networks' feature representation capability for RGB-D SOD. IDR is only adopted in the training phase and is omitted during testing, so it is computationally free. Besides, we propose compact pyramid refinement (CPR) for efficient multi-level feature aggregation to derive salient objects with clear boundaries. With IDR and CPR incorporated, MobileSal performs favorably against state-of-the-art methods on six challenging RGB-D SOD datasets with much faster speed (450fps for the input size of 320 $\times$ 320) and fewer parameters (6.5M). The code is released at https://mmcheng.net/mobilesal.

Jia-Wang Bian, Huangying Zhan, Naiyan Wang et al.

Single-View depth estimation using the CNNs trained from unlabelled videos has shown significant promise. However, excellent results have mostly been obtained in street-scene driving scenarios, and such methods often fail in other settings, particularly indoor videos taken by handheld devices. In this work, we establish that the complex ego-motions exhibited in handheld settings are a critical obstacle for learning depth. Our fundamental analysis suggests that the rotation behaves as noise during training, as opposed to the translation (baseline) which provides supervision signals. To address the challenge, we propose a data pre-processing method that rectifies training images by removing their relative rotations for effective learning. The significantly improved performance validates our motivation. Towards end-to-end learning without requiring pre-processing, we propose an Auto-Rectify Network with novel loss functions, which can automatically learn to rectify images during training. Consequently, our results outperform the previous unsupervised SOTA method by a large margin on the challenging NYUv2 dataset. We also demonstrate the generalization of our trained model in ScanNet and Make3D, and the universality of our proposed learning method on 7-Scenes and KITTI datasets.

Le Zhang, Zenglin Shi, Joey Tianyi Zhou et al.

Is recurrent network really necessary for learning a good visual representation for video based person re-identification (VPRe-id)? In this paper, we first show that the common practice of employing recurrent neural networks (RNNs) to aggregate temporal spatial features may not be optimal. Specifically, with a diagnostic analysis, we show that the recurrent structure may not be effective to learn temporal dependencies than what we expected and implicitly yields an orderless representation. Based on this observation, we then present a simple yet surprisingly powerful approach for VPRe-id, where we treat VPRe-id as an efficient orderless ensemble of image based person re-identification problem. More specifically, we divide videos into individual images and re-identify person with ensemble of image based rankers. Under the i.i.d. assumption, we provide an error bound that sheds light upon how could we improve VPRe-id. Our work also presents a promising way to bridge the gap between video and image based person re-identification. Comprehensive experimental evaluations demonstrate that the proposed solution achieves state-of-the-art performances on multiple widely used datasets (iLIDS-VID, PRID 2011, and MARS).

Xin-Yu Zhang, Le Zhang, Zao-Yi Zheng et al.

Triplet loss has been widely employed in a wide range of computer vision tasks, including local descriptor learning. The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first sample intra-class patches (positives) from the dataset for batch construction and then mine in-batch negatives to form triplets. For high-informativeness triplet collection, researchers mostly focus on mining hard negatives in the second stage, while paying relatively less attention to constructing informative batches. To alleviate this issue, we propose AdaSample, an adaptive online batch sampler, in this paper. Specifically, hard positives are sampled based on their informativeness. In this way, we formulate a hardness-aware positive mining pipeline within a novel maximum loss minimization training protocol. The efficacy of the proposed method is evaluated on several standard benchmarks, where it demonstrates a significant and consistent performance gain on top of the existing strong baselines.

Jia-Wang Bian, Zhichao Li, Naiyan Wang et al.

Recent work has shown that CNN-based depth and ego-motion estimators can be learned using unlabelled monocular videos. However, the performance is limited by unidentified moving objects that violate the underlying static scene assumption in geometric image reconstruction. More significantly, due to lack of proper constraints, networks output scale-inconsistent results over different samples, i.e., the ego-motion network cannot provide full camera trajectories over a long video sequence because of the per-frame scale ambiguity. This paper tackles these challenges by proposing a geometry consistency loss for scale-consistent predictions and an induced self-discovered mask for handling moving objects and occlusions. Since we do not leverage multi-task learning like recent works, our framework is much simpler and more efficient. Comprehensive evaluation results demonstrate that our depth estimator achieves the state-of-the-art performance on the KITTI dataset. Moreover, we show that our ego-motion network is able to predict a globally scale-consistent camera trajectory for long video sequences, and the resulting visual odometry accuracy is competitive with the recent model that is trained using stereo videos. To the best of our knowledge, this is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a long video sequence.

Jia-Wang Bian, Yu-Huan Wu, Ji Zhao et al.

Matching two images while estimating their relative geometry is a key step in many computer vision applications. For decades, a well-established pipeline, consisting of SIFT, RANSAC, and 8-point algorithm, has been used for this task. Recently, many new approaches were proposed and shown to outperform previous alternatives on standard benchmarks, including the learned features, correspondence pruning algorithms, and robust estimators. However, whether it is beneficial to incorporate them into the classic pipeline is less-investigated. To this end, we are interested in i) evaluating the performance of these recent algorithms in the context of image matching and epipolar geometry estimation, and ii) leveraging them to design more practical registration systems. The experiments are conducted in four large-scale datasets using strictly defined evaluation metrics, and the promising results provide insight into which algorithms suit which scenarios. According to this, we propose three high-quality matching systems and a Coarse-to-Fine RANSAC estimator. They show remarkable performances and have potentials to a large part of computer vision tasks. To facilitate future research, the full evaluation pipeline and the proposed methods are made publicly available.

Le Zhang, Zenglin Shi, Ming-Ming Cheng et al.

Nonlinear regression has been extensively employed in many computer vision problems (e.g., crowd counting, age estimation, affective computing). Under the umbrella of deep learning, two common solutions exist i) transforming nonlinear regression to a robust loss function which is jointly optimizable with the deep convolutional network, and ii) utilizing ensemble of deep networks. Although some improved performance is achieved, the former may be lacking due to the intrinsic limitation of choosing a single hypothesis and the latter usually suffers from much larger computational complexity. To cope with those issues, we propose to regress via an efficient "divide and conquer" manner. The core of our approach is the generalization of negative correlation learning that has been shown, both theoretically and empirically, to work well for non-deep regression problems. Without extra parameters, the proposed method controls the bias-variance-covariance trade-off systematically and usually yields a deep regression ensemble where each base model is both "accurate" and "diversified". Moreover, we show that each sub-problem in the proposed method has less Rademacher Complexity and thus is easier to optimize. Extensive experiments on several diverse and challenging tasks including crowd counting, personality analysis, age estimation, and image super-resolution demonstrate the superiority over challenging baselines as well as the versatility of the proposed method.