arXiv subjects

Joachim Keinert

Publications and source records attributed to Joachim Keinert.

4 recordsLinked to original sources

arXiv2025

Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering

Accurate depth estimation is at the core of many applications in computer graphics, vision, and robotics. Current state-of-the-art monocular depth estimators, trained on extensive datasets, generalize well but lack 3D consistency needed for many applications. In this paper, we combine the strength of those generalizing monocular depth estimation techniques with multi-view data by framing this as an analysis-by-synthesis optimization problem to lift and refine such relative depth maps to accurate error-free depth maps. After an initial global scale estimation through structure-from-motion point clouds, we further refine the depth map through optimization enforcing multi-view consistency via photometric and geometric losses with differentiable rendering of the meshed depth map. In a two-stage optimization, scaling is further refined first, and afterwards artifacts and errors in the depth map are corrected via nearby-view photometric supervision. Our evaluation shows that our method is able to generate detailed, high-quality, view consistent, accurate depth maps, also in challenging indoor scenarios, and outperforms state-of-the-art multi-view depth reconstruction approaches on such datasets. Project page and source code can be found at https://lorafib.github.io/ref_depth/.

cs.CV↗

arXiv2023

LiveNVS: Neural View Synthesis on Live RGB-D Streams

Existing real-time RGB-D reconstruction approaches, like Kinect Fusion, lack real-time photo-realistic visualization. This is due to noisy, oversmoothed or incomplete geometry and blurry textures which are fused from imperfect depth maps and camera poses. Recent neural rendering methods can overcome many of such artifacts but are mostly optimized for offline usage, hindering the integration into a live reconstruction pipeline. In this paper, we present LiveNVS, a system that allows for neural novel view synthesis on a live RGB-D input stream with very low latency and real-time rendering. Based on the RGB-D input stream, novel views are rendered by projecting neural features into the target view via a densely fused depth map and aggregating the features in image-space to a target feature map. A generalizable neural network then translates the target feature map into a high-quality RGB image. LiveNVS achieves state-of-the-art neural rendering quality of unknown scenes during capturing, allowing users to virtually explore the scene and assess reconstruction quality in real-time.

cs.CV↗

arXiv2021

Light-field view synthesis using convolutional block attention module

Consumer light-field (LF) cameras suffer from a low or limited resolution because of the angular-spatial trade-off. To alleviate this drawback, we propose a novel learning-based approach utilizing attention mechanism to synthesize novel views of a light-field image using a sparse set of input views (i.e., 4 corner views) from a camera array. In the proposed method, we divide the process into three stages, stereo-feature extraction, disparity estimation, and final image refinement. We use three sequential convolutional neural networks for each stage. A residual convolutional block attention module (CBAM) is employed for final adaptive image refinement. Attention modules are helpful in learning and focusing more on the important features of the image and are thus sequentially applied in the channel and spatial dimensions. Experimental results show the robustness of the proposed method. Our proposed network outperforms the state-of-the-art learning-based light-field view synthesis methods on two challenging real-world datasets by 0.5 dB on average. Furthermore, we provide an ablation study to substantiate our findings.

eess.IV↗

arXiv2019

Learning to Predict Image-based Rendering Artifacts with Respect to a Hidden Reference Image

Image metrics predict the perceived per-pixel difference between a reference image and its degraded (e. g., re-rendered) version. In several important applications, the reference image is not available and image metrics cannot be applied. We devise a neural network architecture and training procedure that allows predicting the MSE, SSIM or VGG16 image difference from the distorted image alone while the reference is not observed. This is enabled by two insights: The first is to inject sufficiently many un-distorted natural image patches, which can be found in arbitrary amounts and are known to have no perceivable difference to themselves. This avoids false positives. The second is to balance the learning, where it is carefully made sure that all image errors are equally likely, avoiding false negatives. Surprisingly, we observe, that the resulting no-reference metric, subjectively, can even perform better than the reference-based one, as it had to become robust against mis-alignments. We evaluate the effectiveness of our approach in an image-based rendering context, both quantitatively and qualitatively. Finally, we demonstrate two applications which reduce light field capture time and provide guidance for interactive depth adjustment.

cs.GR↗