paper-with-me

홈 › Papers

Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos

2023-10-20 · Seoha Kim, Jeongmin Bae, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh

Recent advancements in 4D scene reconstruction using neural radiance fields (NeRF) have demonstrated the ability to represent dynamic scenes from multi-view videos. However, they fail to reconstruct the dynamic scenes and struggle to fit even the training views in unsynchronized settings. It happens because they employ a single latent embedding for a frame while the multi-view images at the same frame were actually captured at different moments. To address this limitation, we introduce time offsets for individual unsynchronized videos and jointly optimize the offsets with NeRF. By design, our method is applicable for various baselines and improves them with large margins. Furthermore, finding the offsets naturally works as synchronizing the videos without manual effort. Experiments are conducted on the common Plenoptic Video Dataset and a newly built Unsynchronized Dynamic Blender Dataset to verify the performance of our method. Project page: https://seoha-kim.github.io/sync-nerf

📄 PDF Abstract BibTeX arXiv:2310.13356

Code (1)

seoha-kim/Sync-NeRF 공식 구현 pytorch

Tasks

NeRF

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…
RoIPool 설명 없음

Similar Papers 제목 키워드 기반

EvDNeRF: Reconstructing Event Data with Dynamic Neural Radiance Fields

2023-10-03 · Anish Bhattacharya, Ratnesh Madaan, Fernando Cladera, Sai Vemprala 외

We present EvDNeRF, a pipeline for generating event data and training an event-based dynamic NeRF, for the purpose of faithfully reconstructing eventstreams on scenes with rigid and non-rigid deformations that may be too…

NeRF

Humans as a Calibration Pattern: Dynamic 3D Scene Reconstruction from Unsynchronized and Uncalibrated Videos

2024-12-26 · Changwoon Choi, Jeongjun Kim, Geonho Cha, Minkwan Kim 외

Recent works on dynamic neural field reconstruction assume input from synchronized multi-view videos with known poses. These input constraints are often unmet in real-world setups, making the approach impractical. We dem…

3D Scene ReconstructionNeRF

SyncTrack4D: Cross-Video Motion Alignment and Video Synchronization for Multi-Video 4D Gaussian Splatting

2025-12-03 · Yonghan Lee, Tsung-Wei Huang, Shiv Gehlot, Jaehoon Choi 외 arxiv

Modeling dynamic 3D scenes is challenging due to their high-dimensional nature, which requires aggregating information from multiple views to reconstruct time-evolving 3D geometry and motion. We present a novel multi-vid…

HyperFields: Towards Zero-Shot Generation of NeRFs from Text

2023-10-26 · Sudarshan Babu, Richard Liu, Avery Zhou, Michael Maire 외

We introduce HyperFields, a method for generating text-conditioned Neural Radiance Fields (NeRFs) with a single forward pass and (optionally) some fine-tuning. Key to our approach are: (i) a dynamic hypernetwork, which l…

NeRF

Uncertainty Error Modeling for Non-Linear State Estimation With Unsynchronized SCADA and $μ$PMU Measurements

2022-12-20 · Austin Cooper, Arturo Bretas, Sean Meyn, Newton G. Bretas

Distribution systems of the future smart grid require enhancements to the reliability of distribution system state estimation (DSSE) in the face of low measurement redundancy, unsynchronized measurements, and dynamic loa…

State Estimation