Michael Rudolph

Michael Rudolph

Auto-generated profile, based on publicly available information

Michael Rudolph

Lebiniz University Hannover, Hannover, Germany

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 May 2022
Verified
Conference Paper
Open access
MRMichael Rudolph
Michael Rudolph
YDYoussef Dawoud
Youssef Dawoud
RGRonja Güldenring
Ronja Güldenring
LNLazaros Nalpantidis
Lazaros Nalpantidis
VBVasileios Belagiannis
Vasileios Belagiannis
We present a lightweight encoder-decoder architecture for monocular depth estimation, specifically designed for embedded platforms. Our main contribution is the Guided Upsampling Block (GUB) for building the decoder of our model. Motivated by the concept of guided image filtering, GUB relies on the image to guide the decoder on upsampling the feature representation and the depth map reconstruction, achieving high resolution results with fine-grained details. Based on multiple GUBs, our model outperforms the related methods on the NYU Depth V2 dataset in terms of accuracy while delivering up to 35.1 fps on the NVIDIA Jetson Nano and up to 144.5 fps on the NVIDIA Xavier NX. Similarly, on the KITTI dataset, inference is possible with up to 23.7 fps on the Jetson Nano and 102.9 fps on the Xavier NX. Our code and models are made publicly available14https://github.com/mic-rud/GuidedDecoding.

7 June 2023
Verified
Conference Paper
Open access
MRMichael Rudolph
Michael Rudolph
SSStefan Schneegass
Stefan Schneegass
ARAmr Rizk
Amr Rizk
Point clouds are a mature representation format for volumetric objects in 6 degrees-of-freedom multimedia streaming. To handle the massive size of point cloud data for visually satisfying immersive media, MPEG standardized Video-based Point Cloud Compression (V-PCC), leveraging existing video codecs to achieve high compression ratios. A major challenge of V-PCC is the high encoding latency, which results in fallback solutions that exchange the compression ratio for faster point cloud codecs. This encoding effort rises significantly in adaptive streaming systems, where heterogeneous user requirements translate into a set of quality representations of the media. In this paper, we show that given one high quality media representation we can achieve live transcoding of video-based compressed point clouds to serve heterogeneous user quality requirements in real time. This stands in contrast to the slow, baseline transcoding that reconstructs and re-encodes the raw point cloud at a new quality setting. To address the high latency when employing the decoder-encoder stack of V-PCC during transcoding, we propose RABBIT, a novel technique that only re-encodes the underlying video sub-streams. This eliminates the overhead of the baseline decoding-encoding approach and decreases the latency further by applying optimized video codecs. We perform extensive evaluation of RABBIT in combination with different video codecs, showing on-par quality with the baseline V-PCC transcoding. Using a hardware-accelerated video codec we demonstrate live transcoding performance of RABBIT and finally present a trade-off between rate, distortion and transcoding latency.

11 September 2025 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
MRMichael Rudolph
Michael Rudolph
SSStefan Schneegass
Stefan Schneegass
ARAmr Rizk
Amr Rizk
Dynamic Point Clouds are a representation for three-dimensional (3D) immersive media that allows users to freely navigate a scene while consuming the content. However, this comes at the cost of substantial data size, requiring efficient compression techniques to make point cloud videos accessible. Addressing this, Video-based Point Cloud Compression (V-PCC) projects points into 2D patches to compress video frames, leveraging the high compression efficiency of legacy video codecs and exploiting temporal correlations in the two-dimensional (2D) images. However, clustering and projecting points into meaningful 2D patches is computationally intensive, leading to high encoding latency in V-PCC. Applying adaptive streaming techniques, originating from traditional video streaming, multiplies the computational effort as multiple encodings of the same content are required. In this light, transcoding a compressed representation into lower qualities for dynamic adaptation to user requirements is gaining popularity. To address the high latency when employing the full decoder-encoder stack of V-PCC during transcoding, we propose RABBIT, a novel technique that only re-encodes the underlying video sub-streams. This is in contrast to slow V-PCC transcoding that reconstructs and re-encodes the raw point cloud at a new quality setting. By eliminating expensive overhead resulting from calculations based on the 3D space representation, the latency of RABBIT is bounded by the latency of transcoding the underlying video streams, allowing optimized video codec implementations to be used to meet the real-time requirements of adaptive streaming systems. Our evaluations of RABBIT, using various optimized video codec implementations, shows on-par quality with the baseline V-PCC transcoding given a high-quality representation. Given unicast or multicast distribution of a point cloud stream and in-network or edge transcoders, our evaluations show the tradeoff between rate-distortion performance and the required network bandwidth.

15 April 2024
Verified
Conference Paper
Open access
MRMichael Rudolph
Michael Rudolph
ARAron Riemenschneider
Aron Riemenschneider
ARAmr Rizk
Amr Rizk
Progressive coding is a valuable technique for networked immersive media. As users approach objects in an immersive environment, progressive coding enables a gradual improvement of content quality. This effectively reduces bandwidth consumption compared to non-progressive methods that require to fully exchange a content representation by an independent, new representation. In this work, we introduce an approach to progressively code point cloud attributes in a learned manner by compressing quantization residuals of each preceding representation through a learned, lightweight transformation in the entropy bottleneck. This allows to progressively reduce quantization errors using a single model in an end-to-end learning manner given the quantization residuals. In contrast to the state of the art that conditions the compression on a fixed rate-distortion, i.e. it requires an ensemble of models to build an adaptive streaming system, our approach requires only a single model during compression and decompression. We present preliminary results of our method, showing bandwidth savings for the scenario of a user approaching an object and gradually transitioning from low to high quality representations.


2 February 2026
Verified
Conference Paper
Open access
AFAndrew Freeman
Andrew Freeman
MRMichael Rudolph
Michael Rudolph
ARAmr Rizk
Amr Rizk