8 citations · 37 across the 14 of their papers we have counts for
15 papers
OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D Mapping
Zelong Lv, Sicheng Xu, Jianfeng Xiang +5
We present OctWorld, a video diffusion framework with persistent 3D memory for generating explorable, world-consistent, and high-fidelity visual scenes. Given a single image, OctWo…
MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
Lingyu Kong, Ruicheng Li, Ruicheng Wang +4
Monocular geometry estimation has recently achieved impressive performance across diverse scenes. However, state-of-the-art models still face notable distortion in local 3D structu…
FM-VLA: Force-based Memory for Vision-Language-Action Models in Contact-Rich Manipulation
Ruicheng Li, Qixiu Li, Ruichun Ma +8
Vision-language-action (VLA) models have achieved impressive generalization in robotic manipulation, and recent memory-augmented VLAs have relaxed the Markovian assumption by condi…
Map2World: Segment Map Conditioned Text to 3D World Generation
Jaeyoung Chung, Suyoung Lee, Jianfeng Xiang +2
3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising r…
Native and Compact Structured Latents for 3D Generation
Jianfeng Xiang, Xiaoxue Chen, Sicheng Xu +8
Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to cap…
NeAR: Coupled Neural Asset-Renderer Stack
Hong Li, Chongjie Ye, Houyuan Chen +12
Neural asset authoring and neural rendering have traditionally evolved as disjoint paradigms: one generates digital assets for fixed graphics pipelines, while the other maps conven…
MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
Ruicheng Wang, Sicheng Xu, Yue Dong +6
We propose MoGe-2, an advanced open-domain geometry estimation model that recovers a metric scale 3D point map of a scene from a single image. Our method builds upon the recent mon…
Structured 3D Latents for Scalable and Versatile 3D Generation
Jianfeng Xiang, Zelong Lv, Sicheng Xu +6
We introduce a novel 3D generation method for versatile and high-quality 3D asset creation. The cornerstone is a unified Structured LATent (SLAT) representation which allows decodi…
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
Ruicheng Wang, Sicheng Xu, Cassie Dai +4
We present MoGe, a powerful model for recovering 3D geometry from monocular open-domain images. Given a single image, our model directly predicts a 3D point map of the captured sce…
Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors
Ruicheng Wang, Jianfeng Xiang, Jiaolong Yang +1
We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typic…
AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collections
Yue Wu, Sicheng Xu, Jianfeng Xiang +4
Previous animatable 3D-aware GANs for human generation have primarily focused on either the human head or full body. However, head-only videos are relatively uncommon in real life,…
3D-aware Image Generation using 2D Diffusion Models
Jianfeng Xiang, Jiaolong Yang, Binbin Huang +1
In this paper, we introduce a novel 3D-aware image generation method that leverages 2D diffusion models. We formulate the 3D-aware image generation task as multiview 2D image set g…
GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds
Jianfeng Xiang, Jiaolong Yang, Yu Deng +1
Recent works have shown that 3D-aware GANs trained on unstructured single image collections can generate multiview images of novel instances. The key underpinnings to achieve this…
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation
Jinheng Xie, Jianfeng Xiang, Junliang Chen +3
While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), s…
GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation
Yu Deng, Jiaolong Yang, Jianfeng Xiang +1
3D-aware image generative modeling aims to generate 3D-consistent images with explicitly controllable camera poses. Recent works have shown promising results by training neural rad…