Alexandre Morgand
@Almorgand
Computer Vision Research Scientist at @simulon, music lover , fond of scientific/musical/geeky/useless stuff. I'm posting papers on whatever I found amazing :)
Oh by the way, I have embarked on a new adventure as a Research Scientist in Computer vision at @Simulon 🎉. I couldn't be more excited about the opportunities and challenges that lie ahead in making VFX available for everyone and empowering creators. Stay tuned!
LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping" TL;DR: Pretty images that are anamorphic through mirror and lenses through diffusion models
"Reconstruct, Inpaint, Finetune: Dynamic Novel-view Synthesis from Monocular Videos" TL;DR : Video diffusion model for dynamic novel-view synthesis trained in a self-supervised manner using only 2D videos. Novel-view synthesis as a structured inpainting task: (2/3)
"How long do you think about the ROMAN empire" My ROMAN empire:
ROMAN(Robust Object Map Alignment Anywhere) github.com/mit-acl/roman a view-invariant global localization method that maps open-set objects and uses the geometry, shape, and semantics of objects to find the transformation between a current pose and previously created object map.
in case you are wondering this is academia now
ICML’s Statement about subversive hidden LLM prompts We live in a weird timeline…
"Learning Temporally Consistent Video Depth from Video Diffusion Priors" TL;DR: ChronoDepth addresses the challenge of streamed video depth estimation with video diffusion model.