activity
20192026
most citedMemoVis: A GenAI-Powered Tool for Creating Companion Reference Images for 3D Design Feedback

11 citations · 34 across the 34 of their papers we have counts for

collaborators
Showing 2024Show all

11 papers · 1 filter

cs.CV2024

Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects

Amir Barda, Matheus Gadelha, Vladimir G. Kim +3

We propose a generative technique to edit 3D shapes, represented as meshes, NeRFs, or Gaussian Splats, in approximately 3 seconds, without the need for running an SDS type of optim…

cs.CV2024

SAMa: Material-aware 3D Selection and Segmentation

Michael Fischer, Iliyan Georgiev, Thibault Groueix +3

Decomposing 3D assets into material parts is a common task for artists, yet remains a highly manual process. In this work, we introduce Select Any Material (SAMa), a material selec…

cs.HC2024★ 11 cited

MemoVis: A GenAI-Powered Tool for Creating Companion Reference Images for 3D Design Feedback

Chen Chen, Cuong Nguyen, Thibault Groueix +2

Providing asynchronous feedback is a critical step in the 3D design workflow. A common approach to providing feedback is to pair textual comments with companion reference images, w…

cs.CV2024

DECOLLAGE: 3D Detailization by Controllable, Localized, and Learned Geometry Enhancement

Qimin Chen, Zhiqin Chen, Vladimir G. Kim +3

We present a 3D modeling method which enables end-users to refine or detailize 3D shapes using machine learning, expanding the capabilities of AI-assisted 3D content creation. Give…

cs.CV2024

MeshUp: Multi-Target Mesh Deformation via Blended Score Distillation

Hyunwoo Kim, Itai Lang, Noam Aigerman +3

We propose MeshUp, a technique that deforms a 3D mesh towards multiple target concepts, and intuitively controls the region where each concept is expressed. Conveniently, the conce…

cs.CV2024

Temporal Residual Jacobians For Rig-free Motion Transfer

Sanjeev Muralikrishnan, Niladri Shekhar Dutt, Siddhartha Chaudhuri +4

We introduce Temporal Residual Jacobians as a novel representation to enable data-driven motion transfer. Our approach does not assume access to any rigging or intermediate shape k…