1 citations · 2 across the 9 of their papers we have counts for
10 papers · 1 filter
Reflection-aware Generative Novel View Synthesis
GeonU Kim, Shin Dong-Yeon, Tae-Hyun Oh
We propose Ref-GeNVS, a training-free, reflection-aware method for generative novel view synthesis (NVS) in mirror scenes. Existing multi-view diffusion models often fail to recogn…
Extracting Neural Materials from 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…
SplatReasoner: Enhancing Embodied Reasoning and Grounding by Novel View Synthesis
Kim Yu-Ji, Dahye Lee, Kim Jun-Seong +6
Vision-Language Models (VLMs) have demonstrated strong reasoning capabilities over images and videos, yet their application to embodied scene understanding often constrained by the…
Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration
Kim Jun-Seong, GeonU Kim, Kim Yu-Ji +3
We introduce Dr. Splat, a novel approach for open-vocabulary 3D scene understanding leveraging 3D Gaussian Splatting. Unlike existing language-embedded 3DGS methods, which rely on…
MeTTA: Single-View to 3D Textured Mesh Reconstruction with Test-Time Adaptation
Kim Yu-Ji, Hyunwoo Ha, Kim Youwang +3
Reconstructing 3D from a single view image is a long-standing challenge. One of the popular approaches to tackle this problem is learning-based methods, but dealing with the test c…
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…
FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields
GeonU Kim, Kim Youwang, Tae-Hyun Oh
We present FPRF, a feed-forward photorealistic style transfer method for large-scale 3D neural radiance fields. FPRF stylizes large-scale 3D scenes with arbitrary, multiple style r…
Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering
Kim Youwang, Tae-Hyun Oh, Gerard Pons-Moll
We present Paint-it, a text-driven high-fidelity texture map synthesis method for 3D meshes via neural re-parameterized texture optimization. Paint-it synthesizes texture maps from…