We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| zzh-tech/ESTRNN | canonical | 7 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| L1 | Ran | zzh-tech/ESTRNN/train/loss.py code served (permissive licence) · get_code("308d7e741a6c1d7e") |
| MSE | Ran | zzh-tech/ESTRNN/train/loss.py code served (permissive licence) · get_code("4e215f323ed97be2") |
| conv1x1 | Ran | zzh-tech/ESTRNN/model/arches.py code served (permissive licence) · get_code("9bed061f167dd318") |
| conv3x3 | Ran | zzh-tech/ESTRNN/model/arches.py code served (permissive licence) · get_code("f3d374db4177f20c") |
| conv5x5 | Ran | zzh-tech/ESTRNN/model/arches.py code served (permissive licence) · get_code("05b9fb4be8292106") |
| feed | Ran | zzh-tech/ESTRNN/model/ESTRNN-RAW.py code served (permissive licence) · get_code("ea472692c3b00532") |
| logsumexp_2d | Ran | zzh-tech/ESTRNN/model/attention.py code served (permissive licence) · get_code("7abfa32a2f1d7424") |
| Perceptual | Not yet run | zzh-tech/ESTRNN/train/loss.py code served (permissive licence) · get_code("d5547b4f6d4c8ae9") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Real-world video deblurring in real time still remains a challenging task due to the complexity of spatially and temporally varying blur itself and the requirement of low computational cost. To improve the network efficiency, we adopt residual dense blocks into RNN cells, so as to efficiently extract the spatial features of the current frame. Furthermore, a global spatio-temporal attention module is proposed to fuse the effective hierarchical features from past and future frames to help better deblur the current frame. Another issue that needs to be addressed urgently is the lack of a real-world benchmark dataset. Thus, we contribute a novel dataset (BSD) to the community, by collecting paired blurry/sharp video clips using a co-axis beam splitter acquisition system. Experimental results show that the proposed method (ESTRNN) can achieve better deblurring performance both quantitatively and qualitatively with less computational cost against state-of-the-art video deblurring methods. In addition, cross-validation experiments between datasets illustrate the high generality of BSD over the synthetic datasets. The code and dataset are released at https://github.com/zzh-tech/ESTRNN.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.16028")
get_code_for_paper("2106.16028")
have("2106.16028")
Connect an agent — have() is free.