SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration
Free-Viewpoint Video (FVV) has emerged as a cornerstone of next-generation immersive media systems and attracted widespread attention. Previous methods primarily focus on short video sequences and suffer from significant performance degradation when processing long-horizon free-viewpoint video (LFVV). Motivated by bit allocation theory, we analyze dynamic-anchor-based volumetric video representation within a rate-distortion optimization framework and propose \textbf{SoLAR}, which is the first error-resilient streamable FVV framework that maintains stable reconstruction quality on long sequences without requiring group-of-pictures partitioning. We propose the Anchor Activation Dynamics (AAD), which enables dynamic anchors to model non-rigid transformations by dynamically activating informative anchors and suppressing redundant ones. Furthermore, we introduce Latent Discrepancy Aware Recalibration (LaDAR), which is a mechanism to identify discrepancies between latent representations and recalibrate the correspondences encoded in the network, effectively mitigating error propagation in LFVV without compromising real-time performance or storage compactness. Extensive experiments demonstrate that \textbf{SoLAR} achieves state-of-the-art reconstruction performance while maintaining minimum storage overhead, which provides a new direction for LFVV reconstruction and advances the practical deployment of immersive systems. Demo free-viewpoint videos are provided in the supplementary material.
Code (0)
등록된 구현이 없습니다.
Tasks
Video ReconstructionSimilar Papers 제목 키워드 기반
Multi-time-horizon Solar Forecasting Using Recurrent Neural Network
The non-stationarity characteristic of the solar power renders traditional point forecasting methods to be less useful due to large prediction errors. This results in increased uncertainties in the grid operation, thereb…
3D Anomaly Detection and SegmentationPredictionMulti-time-horizon Solar Forecasting Using Recurrent Neural Network
The non-stationarity characteristic of the solar power renders traditional point forecasting methods to be less useful due to large prediction errors. This results in increased uncertainties in the grid operation, thereb…
PredictionSolar Irradiance Forecasting with Transformer Model
Solar energy is one of the most popular sources of renewable energy today. It is therefore essential to be able to predict solar power generation and adapt energy needs to these predictions. This paper uses the Transform…
modelPredictionSolar Irradiance ForecastingIntra-day Solar and Power Forecast for Optimization of Intraday Market Participation
The prediction of solar irradiance enhances reliability in photovoltaic (PV) solar plant generation and grid integration. In Colombia, PV plants face penalties if energy production deviates beyond governmental thresholds…
Quantifying the Dunkelflaute: An analysis of variable renewable energy droughts in Europe
Variable renewable energy droughts, also referred to as "Dunkelflaute", emerge as a challenge for realizing climate-neutral energy systems based on variable wind and solar power. Using data on 38 historic weather years a…