Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works52 from public data
- Richer Convolutional Features for Edge Detection1,240
RCF encapsulates all convolutional features into more discriminative representation, which makes good usage of rich feature hierarchies, and is amenable to training via backpropagation, and achieves state-of-the-art performance on several available datasets.
- 638
- NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior378
Experiments on real-world indoor and outdoor scenes show that this method can handle challenging camera trajectories and outperforms existing methods in terms of novel view rendering quality and pose estimation accuracy.
- 275
- Unsupervised Scale-Consistent Depth Learning from Video226
A monocular depth estimation method SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time and the proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training.
- Visual Odometry Revisited: What Should Be Learnt?207
This work revisit the basics of VO and explore the right way for integrating deep learning with epipolar geometry and Perspective-n-Point method and design a simple but robust frame-to-frame VO algorithm (DF-VO) which outperforms pure deep learning-based and geometry-based methods.
- MobileSal: Extremely Efficient RGB-D Salient Object Detection176
This article proposes an implicit depth restoration (IDR) technique to strengthen the mobile networks’ feature representation capability for RGB-D SOD, and proposes compact pyramid refinement (CPR) for efficient multi-level feature aggregation to derive salient objects with clear boundaries.
- SC-DepthV3: Robust Self-Supervised Monocular Depth Estimation for Dynamic Scenes134
This work introduces an external pretrained monocular depth estimation model for generating single-image depth prior, namely pseudo-depth, based on which it proposes novel losses to boost self-supervised training and demonstrates the significantly superior performance of the method over previous methods on six challenging datasets.
- 132
- 123
- Semantic Edge Detection with Diverse Deep Supervision113
A novel fully convolutional neural network using diverse deep supervision within a multi-task framework where bottom layers aim at generating category-agnostic edges, while top layers are responsible for the detection of category-aware semantic edges is proposed.
- Auto-Rectify Network for Unsupervised Indoor Depth Estimation89
This work establishes that the complex ego-motions exhibited in handheld settings are a critical obstacle for learning depth, and proposes an Auto-Rectify Network with novel loss functions, which can automatically learn to rectify images during training.
- HFS: Hierarchical Feature Selection for Efficient Image Segmentation69
This paper proposes a real-time system, Hierarchical Feature Selection (HFS), that performs image segmentation at a speed of 50 frames-per-second, and can be used in a variety computer vision tasks that are built on top ofimage segmentation and superpixel extraction.
- DEL: Deep Embedding Learning for Efficient Image Segmentation53
A novel method called DEL (deep embedding learning) which can efficiently transform superpixels into image segmentation which can achieve comparable segments when compared with MCG but is much faster than it, i.e. 11.4fps vs. 0.07fps.
- Ordered or Orderless: A Revisit for Video Based Person Re-Identification52
This paper presents a simple yet surprisingly powerful approach for VPRe-id, where it is shown that the common practice of employing recurrent neural networks to aggregate temporal-spatial features may not be optimal and provides an error bound that sheds light upon how could the authors improve VP re-identification.
- Neural Refinement for Absolute Pose Regression with Feature Synthesis49
A test-time refinement pipeline that leverages implicit geometric constraints using a robust feature field to enhance the ability of APR methods to use 3D information during inference and introduces a novel Neural Feature Synthesizer model, which encodes 3D geometric features during training and directly renders dense novel view features at test time to refine APR methods.
- When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models49
This survey provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data, and examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue.
- 44
- Diverse Knowledge Distillation for End-to-End Person Search42
This paper proposes a simple yet strong end-to-end network with diverse knowledge distillation to break the bottleneck of person search and designs a spatial-invariant augmentation to assist model to be invariant to inaccurate detection results.
- 38
- Unsupervised Depth Learning in Challenging Indoor Video: Weak Rectification to Rescue.33
This work establishes that the degenerate camera motions exhibited in handheld settings are a critical obstacle for unsupervised depth learning and proposes a novel data pre-processing method for effective training, i.e., search for image pairs with modest translation and remove their rotation via the proposed weak image rectification.
- Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenes30
This paper incorporates optical flow into monocular depth estimation, allowing the model to distinguish between dynamic and static regions in multi-frame inputs, and proposes an attention-based depth network that effectively integrates information from feature maps at different resolutions by incorporating both channel and non-local attention mechanisms.
- 27
- PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction26
The pose residual field (PoRF) is introduced, a novel implicit representation that uses an MLP for regressing pose updates that is more robust than the conventional pose parameter optimisation due to parameter sharing that leverages global information over the entire sequence.
- MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices19
A novel multi-view RGBD dataset captured using a mobile device is introduced, which includes highly precise 3D ground-truth annotations for 153 object models featuring a diverse set of 3D structures.
- 16
- Towards Domain-agnostic Depth Completion15
This work presents 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, using a single image depth prediction network trained on large-scale datasets.
- EponaV2: Driving World Model with Comprehensive Future Reasoning12
This paper proposes EponaV2, a novel paradigm of driving world models, which achieves high-quality planning with comprehensive future reasoning, and introduces a flow matching group relative policy optimization mechanism to further improve planning accuracy.
- Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting12
This work introduces PM-Loss, a novel regularization loss based on a pointmap predicted by a pre-trained transformer that significantly improves the feed-forward 3DGS across various architectures and scenes, delivering consistently better rendering results.
- Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs9
An in-depth analysis reveals that 3D scene-centric VLMs show limited reliance on the 3D scene encoder, and the pre-train stage appears less effective than in 2D VLMs, and that data scaling benefits are less pronounced on larger datasets.
- OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving9
This work proposes OminiGen, which generates aligned multimodal sensor data in a unified framework and designs a novel generalizable multimodal reconstruction method, UAE, to jointly decode LiDAR and multi-view camera data.
- Hyper3D: Efficient 3D Representation via Hybrid Triplane and Octree Feature for Enhanced 3D Shape Variational Auto-Encoders7
Hyper3D is introduced, which enhances VAE reconstruction through efficient 3D representation that integrates hybrid triplane and octree features and outperforms traditional representations by reconstructing 3D shapes with higher fidelity and finer details, making it well-suited for 3D generation pipelines.
- SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting6
This work proposes 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.
- 6
- 6
- 6
- 5
- Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective4
A 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, and outlines future directions to address open challenges such as scalability, evaluation standards, and world modeling.
- PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space4
PixWorld is introduced, a single model that jointly addresses 3D reconstruction and generation that consistently outperforms prior latent-space generation methods and matches state-of-the-art reconstruction methods, demonstrating the superiority of a unified pixel-space approach.
- RoboPearls: Editable Video Simulation for Robot Manipulation4
RoboPearls, an editable video simulation framework for robotic manipulation that automates the simulation production process in a user-friendly manner through flexible command interpretation and execution, and employs a vision-language model (VLM) to analyze robotic learning issues to close the simulation loop for performance enhancement.
- 3
- 3
- Deep negative correlation classification2
This work proposes 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.
- 2
- 1
- Image Matching Benchmark1
This work presents the first application-oriented image matching benchmark to facilitate the analysis of matching algorithms in application level and demonstrates the effectiveness of a simple technique which is readily pluggable into any matching system to improve performance.
- –
- Self-supervised Video Depth Adaptation for Efficient Sparse-view NeRF–
This work presents a novel method that self-supervisedly adapts a pretrained video depth estimation network to each specific scene, which enables high-fidelity depth estimation even under extreme view sparsity and significantly accelerates neural radiance field (NeRF) training.
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.