OoD-Pose: Camera Pose Regression From Out-of-Distribution Synthetic Views

Ng, Tony; Lopez-Rodriguez, Adrian; Balntas, Vassileios; Mikolajczyk, Krystian

doi:10.1109/3dv57658.2022.00082

Cited by 2 publications

(2 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baselines. We compare our method with SCRNet [1], SCRNet-ID [77], and SRC [78]. SCRNet is the regressiononly baseline proposed by [1], based on which we built SCRNet-ID and E-SCRNet.…”

Section: B Camera Pose Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Hallucinated Neural Radiance Fields in the Wild

Chen

Zhang

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Neural Radiance Fields (NeRF) have been proposed for photorealistic novel view rendering. However, it requires many different views of one scene for training. Moreover, it has poor generalizations to new scenes and requires retraining or finetuning on each scene. In this paper, we develop a new NeRF model for novel view synthesis using only a single image as input. We propose to combine the (coarse) planar rendering and the (fine) volume rendering to achieve higher rendering quality and better generalizations. We also design a depth teacher net that predicts dense pseudo depth maps to supervise the joint rendering mechanism and boost the learning of consistent 3D geometry. We evaluate our method on three challenging datasets. It outperforms state-of-the-art single-view NeRFs by achieving 5∼20% improvements in PSNR and reducing 20∼50% of the errors in the depth rendering. It also shows excellent generalization abilities to unseen data without the need to finetune on each new scene.

show abstract

“…Baselines. We compare our method with SCRNet [1], SCRNet-ID [77], and SRC [78]. SCRNet is the regressiononly baseline proposed by [1], based on which we built SCRNet-ID and E-SCRNet.…”

Section: B Camera Pose Estimationmentioning

confidence: 99%

“…SCRNet is the regressiononly baseline proposed by [1], based on which we built SCRNet-ID and E-SCRNet. SCRNet-ID utilizes the In-Distribution novel view selection policy proposed by [77] to obtain new synthetic views. SRC [78] is a recently proposed classification-based method for few-views scene-specific localization.…”

Section: B Camera Pose Estimationmentioning

confidence: 99%