From the 1 of 7 linked papers with an AI index.
7 papers
SplatReasoner: Enhancing Embodied Reasoning and Grounding by Novel View Synthesis
Kim Yu-Ji, Dahye Lee, Kim Jun-Seong +6
SplatReasoner integrates query‑conditioned novel view synthesis via 3D Gaussian splatting into vision‑language models, enabling better embodied reasoning and 3D grounding by genera…
Extracting Neural Materials from Multi-view Images
Kim Youwang, Jon Hasselgren, Peter Kocsis +3
Neural materials can represent complex specular reflections and scattering effects in a compact, universal basis. However, acquiring and authoring such materials remains challengin…
FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Image
Kim Youwang, Zhengyu Yang, Liuhao Ge +8
We introduce FiCA, a Feed-forward, instant Gaussian Codec Avatar generation pipeline that creates lifelike avatars from a single portrait image. Generating a photorealistic and dri…
HDR-NSFF: High Dynamic Range Neural Scene Flow Fields
Shin Dong-Yeon, Kim Jun-Seong, Kwon Byung-Ki +1
Radiance of real-world scenes typically spans a much wider dynamic range than what standard cameras can capture. While conventional HDR methods merge alternating-exposure frames, t…
Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild
Junhyeong Cho, Kim Youwang, Hunmin Yang +1
Recent monocular 3D shape reconstruction methods have shown promising zero-shot results on object-segmented images without any occlusions. However, their effectiveness is significa…
FPGS: Feed-Forward Semantic-aware Photorealistic Style Transfer of Large-Scale Gaussian Splatting
GeonU Kim, Kim Youwang, Lee Hyoseok +1
We present FPGS, a feed-forward photorealistic style transfer method of large-scale radiance fields represented by Gaussian Splatting. FPGS, stylizes large-scale 3D scenes with arb…