Diogo Luvizon
@DiogoLuvizon
Followers
106
Following
489
Statuses
69
Postdoctoral Researcher, Max Planck Institute for Informatics
Germany
Joined January 2010
0
0
1
RT @VGolyanik: Virtual humans also travelling to #ECCV2024: 1) Luvizon et al. Relightable Neural Actor. tl;dr: Video-based @DiogoLuvizon's…
0
16
0
Working on human relighting for #CVPR? Pytorch code and dataset will be released in the next few weeks, stay tuned!
Check out our #ECCV Relightable Neural Actor! It provides pose and light control, self shadows, surface wrinkles, and material editing at inference time! Project: Team: @DiogoLuvizon, @VGolyanik, @AdamKortylewski, @marc_habermann, C. Theobalt
0
3
7
RT @jianwang_mpi: Wanna track accurate 3D motion from a VR/AR headset? 🕶️ Discover how we tackle egocentric pose estimation! Join us at #CV…
0
16
0
RT @jianwang_mpi: Check out our work “Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement,�� which is…
0
25
0
@JuuCustodio Também é usada pra fazer publicidade de pesquisa científica. É o link3dIN dos pesquisadores 😅
1
0
1
RT @marc_habermann: Happy to present Holoported Characters, which is accepted at #CVPR2024 :) Let our virtual avatar explain our method to…
0
15
0
@david_picard @CSProfKGD @MKBHD Good point. This week a traditional Brazilian magazine published this. Count the number of fingers. Of course, they are saying it was on purpose.
1
0
2
RT @VGolyanik: Interested in monocular 3D tracking of interacting and fast-moving hands 👏🙏🙌, possibly under low-light conditions? This is p…
0
15
0
@david_picard For individual tensors you can use persistent=False; but I'm not sure it works for Module. In general, I do it in the painful way by keeping a list per group of the layers that I want to save or load ;)
0
0
1
RT @jianwang_mpi: How to improve 3D human pose estimation from egocentric images? SceneEgo makes it easier! Do not forget to join our talk…
0
15
0
Amazing work from @jianwang_mpi and @VcaiMpi now at #CVPR2023 : How to improve 3D human pose estimation from egocentric images? SceneEgo makes it easier! Check out source code, demo and new dataset at: - project: - github:
0
3
8
RT @_akhaliq: Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold paper page: htt…
0
6K
0
RT @VGolyanik: #EurographicsC 2023 kicks off today. We contributed two full papers and one STAR: Tuesday, 9 am,…
0
11
0
RT @VGolyanik: MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis Our new work on synthesising long and realistic 3D hum…
0
15
0