Sculpt3d: Multi-view consistent text-to-3d generation with sparse 3d prior

C Chen, X Yang, F Yang, C Feng… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Recent works on text-to-3d generation show that using only 2D diffusion supervision for 3D
generation tends to produce results with inconsistent appearances (eg faces on the back …

Taps3d: Text-guided 3d textured shape generation from pseudo supervision

J Wei, H Wang, J Feng, G Lin… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
In this paper, we investigate an open research task of generating controllable 3D textured
shapes from the given textual descriptions. Previous works either require ground truth …

Reacto: Reconstructing articulated objects from a single video

C Song, J Wei, CS Foo, G Lin… - Proceedings of the IEEE …, 2024‏ - openaccess.thecvf.com
In this paper we address the challenge of reconstructing general articulated 3D objects from
a single video. Existing works employing dynamic neural radiance fields have advanced the …

Attrihuman-3d: Editable 3d human avatar generation with attribute decomposition and indexing

F Yang, T Chen, X He, Z Cai, L Yang… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Editable 3D-aware generation which supports user-interacted editing has witnessed rapid
development recently. However existing editable 3D GANs either fail to achieve high …

Weakly-supervised 3d pose transfer with keypoints

J Chen, C Li, GH Lee - Proceedings of the IEEE/CVF …, 2023‏ - openaccess.thecvf.com
The main challenges of 3D pose transfer are: 1) Lack of paired training data with different
characters performing the same pose; 2) Disentangling pose and shape information from the …

Moda: Modeling deformable 3d objects from casual videos

C Song, J Wei, T Chen, Y Chen, CS Foo, F Liu… - International Journal of …, 2024‏ - Springer
In this paper, we focus on the challenges of modeling deformable 3D objects from casual
videos. With the popularity of NeRF, many works extend it to dynamic scenes with a …

Geometry-aware 3D pose transfer using transformer autoencoder

S Liu, S Gai, F Da, F Waris - Computational Visual Media, 2024‏ - Springer
Abstract 3D pose transfer over unorganized point clouds is a challenging generation task,
which transfers a source's pose to a target shape and keeps the target's identity. Recent …

Magicpose4d: Crafting articulated models with appearance and motion control

H Zhang, D Chang, F Li, M Soleymani… - arxiv preprint arxiv …, 2024‏ - arxiv.org
With the success of 2D and 3D visual generative models, there is growing interest in
generating 4D content. Existing methods primarily rely on text prompts to produce 4D …

Sync4d: Video guided controllable dynamics for physics-based 4d generation

Z Fu, J Wei, W Shen, C Song, X Yang, F Liu… - arxiv preprint arxiv …, 2024‏ - arxiv.org
In this work, we introduce a novel approach for creating controllable dynamics in 3D-
generated Gaussians using casually captured reference videos. Our method transfers the …

HMR-Adapter: A Lightweight Adapter with Dual-Path Cross Augmentation for Expressive Human Mesh Recovery

W Shen, W Yin, H Wang, C Wei, Z Cai, L Yang… - Proceedings of the 32nd …, 2024‏ - dl.acm.org
Expressive Human Mesh Recovery (HMR) involves reconstructing the 3D human body,
including hands and face, from RGB images. It is difficult because humans are highly …