Khiem Vuong

@kvuongdev

PhD-ing @CMU_Robotics | interning @MetaAI, ex-intern @Apple | Vision, Robotics

Pittsburgh, PA

khiemvuong.com

Replies Reposts Media

Pinned
Khiem Vuong
@kvuongdev
Aug 26
[1/6] Can one model fix rendering artifacts from any 3D representation? And what does it even mean to "fix" a rendering? At #ECCV2026, we present FixAnything (fix-anything.github.io): a single generalist video model that refines 3DGS/mesh/sparse point-cloud renderings into
00:00
7
Khiem Vuong
@kvuongdev
Sep 9
Curious how little finetuning it takes for a video model to clean up rendering artifacts — 3DGS, NeRF, mesh, sparse point clouds — while those same renders give you camera control capabilities? Come check out our poster at #ECCV2026 (ExHall #283) tomorrow!! Sadly I can't be at
Khiem Vuong
@kvuongdev
Aug 26
[1/6] Can one model fix rendering artifacts from any 3D representation? And what does it even mean to "fix" a rendering? At #ECCV2026, we present FixAnything (fix-anything.github.io): a single generalist video model that refines 3DGS/mesh/sparse point-cloud renderings into
00:00
Khiem Vuong
@kvuongdev
Sep 9
If you are curious about how to turn a video model into a multiview novel view synthesis model, come see our poster at #ECCV2026 (ExHall #275) tomorrow!! Sadly I will have to miss ECCV this year, but @qi_wu57 will be there presenting — go say hi! ExHall # 275 at 10:30 AM CEST /
Khiem Vuong
@kvuongdev
Apr 22
[1/7] Video diffusion has come a long way, generating more & more realistic videos. Can we revisit sparse-view novel view synthesis through these video priors? Meet FrameCrafter: a permutation-invariant multi-view model built on video diffusion 🧵 🌐 frame-crafter.github.io
00:00
Khiem Vuong
@kvuongdev
Aug 26
Thanks @orlitany for organizing, had lots of fun discussion! If interested, please also check out FixAnything, the paper I most talked about, here x.com/kvuongdev/stat….
Or Litany ✈️ECCV
@orlitany
Aug 26
Had the pleasure of (virtually) hosting @kvuongdev today at my lab and hear about his awesome work! Thanks for sharing your insights from working on 3D and video models.
Khiem Vuong
@kvuongdev
Aug 26
Thanks @kwangmoo_yi for the post! If interested, please also see our thread here: x.com/kvuongdev/stat….
Kwang Moo Yi
@kwangmoo_yi
Aug 26
Vuong et al., "FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors" Fix intermediate render representations via a fine-tuned video model. Uses LoRA and DPO (with geometric consistency reward)
00:00