55 citations · 110 across the 34 of their papers we have counts for
38 papers
PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
Yaolong Zhu, Peng Li, Jiahao Lu +8
Feed-forward 3D reconstruction models have achieved remarkable progress through large-scale training and strong learned priors. However, they remain fragile when applied to dynamic…
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
Jiahao Lu, Minghao Yin, Wenbo Hu +5
We present a compact geometry-native latent space as a shared foundation for perception and generation. Visual generators can produce photorealistic frames without preserving a con…
WAT3R: Feedforward Underwater 3D Reconstruction
Jiayi Xu, Jiahao Lu, Ziqiang Zheng +4
Reliable feedforward underwater 3D reconstruction remains challenging due to severe light attenuation and backscattering, which degrade visual quality and disrupt feature consisten…
SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers
Minghao Yin, Jiahao Lu, Wenbo Hu +3
Video diffusion transformers address their tokens by position on the pixel-time grid: an address in the tensor, not in the world. The address we would want, the world point a token…
Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor
Yang Zhao, Jiahao Lu, Bin Huang +2
Narang et al. (2021) evaluated 40+ Transformer modifications at T5-base scale and concluded that most did not transfer. Five years later, the typical working regime has moved to 1-…
ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction
Yanzhe Liang, Ruijie Zhu, Hanzhi Chang +3
We present ReFlow, a unified framework for monocular dynamic scene reconstruction that learns 3D motion in a novel self-correction manner from raw video. Existing methods often suf…
MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE
Ruijie Zhu, Jiahao Lu, Wenbo Hu +4
We present MotionCrafter, a framework that leverages video generators to jointly reconstruct 4D geometry and estimate dense motion from a monocular video. The key idea is a joint r…
Prototype-Guided Concept Erasure in Diffusion Models
Yuze Cai, Jiahao Lu, Hongxiang Shi +2
Concept erasure is extensively utilized in image generation to prevent text-to-image models from generating undesired content. Existing methods can effectively erase narrow concept…
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
Jiahao Lu, Jiayi Xu, Wenbo Hu +5
Estimating the 3D trajectory of every pixel from a monocular video is crucial and promising for a comprehensive understanding of the 3D dynamics of videos. Recent monocular 3D trac…
UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass
Mengfei Li, Peng Li, Zheng Zhang +9
We present UniSH, a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction. A key challenge in this domain is the scarcity of large-scale, annotat…
CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
Chengfeng Zhao, Jiazhi Shu, Yubo Zhao +7
In this paper, we find that the generation of 3D human motions and 2D human videos is intrinsically coupled. 3D motions provide the structural prior for plausibility and consistenc…
Frequency Regularization: Unveiling the Spectral Inductive Bias of Deep Neural Networks
Jiahao Lu
Regularization techniques such as L2 regularization (Weight Decay) and Dropout are fundamental to training deep neural networks, yet their underlying physical mechanisms regarding…
TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels
Jiahao Lu, Weitao Xiong, Jiacheng Deng +6
Monocular 3D tracking aims to capture the long-term motion of pixels in 3D space from a single monocular video and has witnessed rapid progress in recent years. However, we argue t…
HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos
Weitao Xiong, Zhiyuan Yuan, Jiahao Lu +3
Monocular dynamic video reconstruction faces significant challenges in dynamic human scenes due to geometric inconsistencies and resolution degradation issues. Existing methods lac…
Reconstructing 4D Spatial Intelligence: A Survey
Yukang Cao, Jiahao Lu, Zhisheng Huang +8
Reconstructing 4D spatial intelligence from visual observations has long been a central yet challenging task in computer vision, with broad real-world applications. These range fro…
MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting
Hanzhi Chang, Ruijie Zhu, Wenjie Chang +5
Surface reconstruction has been widely studied in computer vision and graphics. However, existing surface reconstruction works struggle to recover accurate scene geometry when the…
Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation
Jiahao Lu, Jiacheng Deng
3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels. Currently, transform…
MERA: Multimodal and Multiscale Self-Explanatory Model with Considerably Reduced Annotation for Lung Nodule Diagnosis
Jiahao Lu, Chong Yin, Silvia Ingala +3
Lung cancer, a leading cause of cancer-related deaths globally, emphasises the importance of early detection for better patient outcomes. Pulmonary nodules, often early indicators…
SAS: Segment Any 3D Scene with Integrated 2D Priors
Zhuoyuan Li, Jiahao Lu, Jiacheng Deng +4
The open vocabulary capability of 3D models is increasingly valued, as traditional methods with models trained with fixed categories fail to recognize unseen objects in complex dyn…
Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance Segmentation
Jiahao Lu, Jiacheng Deng, Tianzhu Zhang
3D instance segmentation aims to predict a set of object instances in a scene and represent them as binary foreground masks with corresponding semantic labels. Currently, transform…
Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
Zekai Gu, Rui Yan, Jiahao Lu +9
Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images. However, precise control over the video generation process,…
Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
Jiahao Lu, Tianyu Huang, Peng Li +7
Recent developments in monocular depth estimation methods enable high-quality depth estimation of single-view images but fail to estimate consistent video depth across different fr…
DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering
Jiahao Lu, Jiacheng Deng, Ruijie Zhu +4
Dynamic scenes rendering is an intriguing yet challenging problem. Although current methods based on NeRF have achieved satisfactory performance, they still can not reach real-time…
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
Ruijie Zhu, Yanzhe Liang, Hanzhi Chang +5
Dynamic scene reconstruction is a long-term challenge in the field of 3D vision. Recently, the emergence of 3D Gaussian Splatting has provided new insights into this problem. Altho…