Showing 2026Show all
3 papers · 1 filter
cs.CV2026
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…
cs.CV2026
Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices
Kim Jun-Seong, Mingyu Kim, GeonU Kim +2
We introduce Fact-Hash, a novel parameter-encoding method for training on-device neural radiance fields. Neural Radiance Fields (NeRF) have proven pivotal in 3D representations, bu…
cs.CV2026
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…