67 citations · 128 across the 15 of their papers we have counts for
15 papers
AutoDecoding Latent 3D Diffusion Models
Evangelos Ntavelis, Aliaksandr Siarohin, Kyle Olszewski +3
We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from…
Unsupervised Volumetric Animation
Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov +5
We propose a novel approach for unsupervised 3D animation of non-rigid deformable objects. Our method learns the 3D structure and dynamics of objects solely from single-view RGB vi…
ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes
Ahmed Abdelreheem, Kyle Olszewski, Hsin-Ying Lee +2
The two popular datasets ScanRefer [16] and ReferIt3D [3] connect natural language to real-world 3D data. In this paper, we curate a large-scale and complementary dataset extending…
Cross-Modal 3D Shape Generation and Manipulation
Zezhou Cheng, Menglei Chai, Jian Ren +5
Creating and editing the shape and color of 3D objects require tremendous human effort and expertise. Compared to direct manipulation in 3D interfaces, 2D interactions such as sket…
Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation
Ye Zhu, Yu Wu, Kyle Olszewski +3
Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desidera…
Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulation
Verica Lazova, Vladimir Guzov, Kyle Olszewski +2
We present a novel method for performing flexible, 3D-aware image content manipulation while enabling high-quality novel view synthesis. While NeRF-based approaches are effective f…