24СʱÈÈÃŰæ¿éÅÅÐаñ    

²é¿´: 3476  |  »Ø¸´: 5
¡¾Óн±½»Á÷¡¿»ý¼«»Ø¸´±¾Ìû×Ó£¬²ÎÓë½»Á÷£¬¾ÍÓлú»á·ÖµÃ×÷Õß RSA888 µÄ 4 ¸ö½ð±Ò
µ±Ç°Ö»ÏÔʾÂú×ãÖ¸¶¨Ìõ¼þµÄ»ØÌû£¬µã»÷ÕâÀï²é¿´±¾»°ÌâµÄËùÓлØÌû

RSA888

Ìú³æ (³õÈëÎÄ̳)

[½»Á÷] С°×µÚÒ»´ÎͶ¸åÇë´ó¼Ò°ïæ¿´¿´Éó¸åÒâ¼û¸ÃÔõô»Ø¸´£¿

׿±±ÏҵͶÁËÒ»¸ömdpiÆìϵÄË®¿¯£¬Í¶¸å½«½üÒ»¸öÔÂÊÕµ½ÁËÁ½¸öÉó¸åÈËÒâ¼û£¬È»ºó±à¼­¾Í·¢ÁËÓʼþpending major revision£¬¸øÁË10Ììʱ¼äÒªÇó´óÐÞ£¨µÚÈý¸öÉó¸åÈË»¹Ã»»Ø¸´£©£¬µÚÒ»´ÎͶ¸åûɶ¾­Ñ飬ÏëÇë´ó¼Ò°ïæ²ÎıһÏÂÓ¦¸Ã°´ÕÕʲô·½ÏòÀ´¸ÄÄØ£¿
µÚÒ»¸öÉó¸åÈË´ò·ÖËäÈ»Ïà¶Ô±È½Ï¸ß£¬µ«ÊÇËû¾õµÃ´´ÐÂÐÔ²»¹»½¨ÒéÒÔletterÐÎʽ·¢±í(ÎÒ×Ô¼ºÈ·ÊµÒ²¾õµÃ´´ÐÂÐÔ²»¹»£¬µ«ÊÇ´´ÐµãÕâ¸ö¶«Î÷±È½ÏÖ÷¹Û£¬¶øÇÒͶ¸åµÄ±Ï¾¹ÊÇË®¿¯)£»µÚ¶þ¸öÉó¸åÈËËäÈ»´ò·ÖûÓеÚÒ»¸ö¸ß£¬µ«ÎÊÌâ¶¼Ö±»÷Òªº¦£¬Ó¦¸ÃÊǺܶ®ÐеÄר¼Ò£¬²»¹ý¸Ð¾õÈÏÕæ»Ø´ðÎÊÌ⣬¸ÄÒ»¸Ä²¹³äÒ»µãʵÑ黹ÊDZȽϺùýµÄ£¬Ã»ÓжÔÎÄÕµĴ´ÐÂÐÔÌá³öÖÊÒÉ¡£
ÎÊÌâ¾ÍÊÇÎÒÏÖÔÚ²»ÖªµÀÊÇ·ñÓ¦¸Ã¸Ä³Életter£¬±Ï¾¹ÕâÑù¸Ä¶¯»¹ÊǺܴóµÄ£¬ÓÉÓÚµÚ¶þ¸öÉó¸åÈ˵ÄÎÊÌâÖÐÐèÒªÓв¹³äʵÑéµÄµØ·½£¬ÅÂʱ¼äÀ´²»¼°£¬¶øÇҸijÉletterµÄ»°»á¼õÉٺܶàʵÑ飬²»ÖªµÀµÚ¶þ¸öÉó¸åÈ˻᲻»á²»Í¬Ò⣬µ«ÊDz»¸ÄletterµÄ»°ÓÖŵÚÒ»¸öÉó¸åÈËÖ±½Ó¾Ü£¬»òÕß˵ÓÐûÓÐʲô±È½ÏºÃµÄ·½Ê½»Ø´ðµÚÒ»¸öÉó¸åÈ˹ØÓÚ´´ÐÂÐÔµÄÖÊÒÉÄØ(ͬʱ¿´Éó¸åÒâ¼ûÎҸоõµÚÒ»¸öÉó¸åÈËûÓÐÌØ±ð×Ðϸ¶ÁÎÒµÄÎÄÕ£¬ÓÐЩµØ·½Àí½âµÄ¸úÎÒÏë±í´ïµÄÉõÖÁ¸úµÚ¶þ¸öÉó¸åÈËÀí½âµÄÃ÷ÏÔ²»Ò»Ñù)¡­ÏëÇë´ó¼Ò°ïæ¿´¿´ÕâÖÖÇé¿öÓ¦¸ÃÔõô¸ÄÄØ£¿¸½Í¼·Ö±ðÊǵÚÒ»¸öºÍµÚ¶þ¸öÉó¸åÈ˵Ĵò·Ö
ÏÂÃæÊÇÁ½¸öÉó¸åÈ˵Ä×ÜÌåÒâ¼û£º
Éó¸åÈËÒ»£º
this paper proposed a deep learning based demosaicking method using several existing techniques, such as the unet++ framework, residual in residual dense block, and depthwise separable convolutions. in particular, the framework inserts densely connected layer blocks that adopt depthwise separable convolutions to reduce the number of parameters. the main novelty of the paper is that: deploying the gaussian smoothing layer into the cnn framework can expand the receptive field without down-sampling image size, achieving the fastest execution time and modest quality performance relative to the considered demosaicking methods.??because the novelty in this paper is limited, we recommend that this paper should be revised and shortened for possible publication as a `letter'.
Éó¸åÈ˶þ£º
the authors present a method for fast and efficient demosaicking. the manuscript contains some interesting ideas and experiments comparing the performance of their method to other methods. in general it is well written and easy to read. also the length is sufficient for the topic. my three biggest concerns on the manuscripts are:?
1) by making multiple numbers boldface the focus is taken away from the best performing methods in each of the tables.
2) drawing run-time conclusions from comparing cpu algorithms to gpu algorithms is unfair and favors the gpu versions.
3) the comparison of the cascade: demosaick->classification and just the classification on the original seems to favor the demosaick->classification pipeline because images are greatly reduced in size anyway.
¾ßÌåµÄÒâ¼û¾Í²»·ÅÁË£¬Á½¸öÉó¸åÈË¼ÓÆðÀ´ÌáÁË13Ìõ×óÓÒµÄÎÊÌ⣬°üÀ¨Èò¹³äÖ¸¶¨ÎÄÏ׺ÍÊéд´íÎóÖ®ÀàµÄ

С°×µÚÒ»´ÎͶ¸åÇë´ó¼Ò°ïæ¿´¿´Éó¸åÒâ¼û¸ÃÔõô»Ø¸´£¿


С°×µÚÒ»´ÎͶ¸åÇë´ó¼Ò°ïæ¿´¿´Éó¸åÒâ¼û¸ÃÔõô»Ø¸´£¿-1


·¢×ÔСľ³æAndroid¿Í»§¶Ë
»Ø¸´´ËÂ¥
ÒÑÔÄ   »Ø¸´´ËÂ¥   ¹Ø×¢TA ¸øTA·¢ÏûÏ¢ ËÍTAºì»¨ TAµÄ»ØÌû

nhhaa19

ÖÁ×ðľ³æ (Ö°Òµ×÷¼Ò)

¡ï ¡ï ¡ï
Сľ³æ: ½ð±Ò+0.5, ¸ø¸öºì°ü£¬Ð»Ð»»ØÌû
RSA888: ½ð±Ò+2 2021-04-19 19:56:27
ÎÊÌâ²»´óÂÕÒµ½Éó¸åÈËÖ¸¶¨ÎÄÏ×£¬ÄÇô£¬ÕâÓ¦¸ÃÊÇͨѶ×÷ÕßµÄÎÄÕÂÁË£¬·ÅÔÚµÚÒ»²¿·Ö¾ÍºÃÁË¡£

·¢×ÔСľ³æAndroid¿Í»§¶Ë
3Â¥2021-04-19 18:43:36
ÒÑÔÄ   »Ø¸´´ËÂ¥   ¹Ø×¢TA ¸øTA·¢ÏûÏ¢ ËÍTAºì»¨ TAµÄ»ØÌû
²é¿´È«²¿ 6 ¸ö»Ø´ð

fqcgfqcgfqcg

ľ³æ (ÎÄ̳¾«Ó¢)

¡ï
Сľ³æ: ½ð±Ò+0.5, ¸ø¸öºì°ü£¬Ð»Ð»»ØÌû
¼Ò¼ÒÓб¾ÄÑÄîµÄ¾­

·¢×ÔСľ³æAndroid¿Í»§¶Ë
2Â¥2021-04-19 17:47:10
ÒÑÔÄ   »Ø¸´´ËÂ¥   ¹Ø×¢TA ¸øTA·¢ÏûÏ¢ ËÍTAºì»¨ TAµÄ»ØÌû

zf015222

Ìú¸Ëľ³æ (Ö°Òµ×÷¼Ò)

¡ï ¡ï ¡ï
Сľ³æ: ½ð±Ò+0.5, ¸ø¸öºì°ü£¬Ð»Ð»»ØÌû
RSA888: ½ð±Ò+2 2021-04-19 19:56:35
°´Õձ༭һÌõÒ»Ìõ»Ø´ð£¬Â¼ÓÃÁË£¬·ÅÐÄ¡£

·¢×ÔСľ³æAndroid¿Í»§¶Ë
ÎãÒ⣬Îã±Ø£¬Îã¹Ì£¬ÎãÎÒ!!!
4Â¥2021-04-19 19:10:11
ÒÑÔÄ   »Ø¸´´ËÂ¥   ¹Ø×¢TA ¸øTA·¢ÏûÏ¢ ËÍTAºì»¨ TAµÄ»ØÌû

orangg

гæ (СÓÐÃûÆø)

¡ï
Сľ³æ: ½ð±Ò+0.5, ¸ø¸öºì°ü£¬Ð»Ð»»ØÌû
Ò»Ñù£¬Ò»ÌõÒ»Ìõ»Ø¸´ÖÐ

·¢×ÔСľ³æAndroid¿Í»§¶Ë
5Â¥2021-04-21 15:37:13
ÒÑÔÄ   »Ø¸´´ËÂ¥   ¹Ø×¢TA ¸øTA·¢ÏûÏ¢ ËÍTAºì»¨ TAµÄ»ØÌû
×î¾ßÈËÆøÈÈÌûÍÆ¼ö [²é¿´È«²¿] ×÷Õß »Ø/¿´ ×îºó·¢±í
[»ù½ðÉêÇë] ûÓÐÈκÎÏûÏ¢-ÊDz»ÊǾÍÁ¹ÁË +5 ͼÀ²Í¼À² 2026-08-24 5/250 2026-08-24 17:24 by robertÏè
[»ù½ðÉêÇë] Èç¹û´Ë¿ÌÄãÕýÔÚΪ¹ú»ù¸Ðµ½½¹ÂÇ£¬²»·ÁÀ´ÌýÌýÕâÊס¶»ù½ðÖ®Íâ¡· +5 scalable 2026-08-24 5/250 2026-08-24 17:03 by spiderzhuzhi
[»ù½ðÉêÇë] 2026¹ú×ÔÈ»º¯ÆÀ·Ñµ½ÕË +17 ÑòÑü°å 2026-08-21 19/950 2026-08-24 16:52 by iaeyuan
[»ù½ðÉêÇë] ½¨Òé»ù½ð·¢²¼Ìáǰ¸ø³öÃ÷È·µÄʱ¼äµã +13 kulium 2026-08-21 16/800 2026-08-24 16:27 by superceng
[»ù½ðÉêÇë] ½ñÈÕ²»·Å°ñ£¿Íø´«¹ú×ÔȻԤ¼Æ 8 Ô 27 Èտɲé½á¹û +17 ҽѧÀÏÄк¢ 2026-08-20 21/1050 2026-08-24 14:21 by refreshing11
[»ù½ðÉêÇë] ¹À¼ÆÊÇÖÜËÄ +4 archvillain 2026-08-18 4/200 2026-08-24 13:53 by zzuzxg
[»ù½ðÉêÇë] ÈÃÎÒÖÐÒ»¸öÃæÉϰɣ¡ +13 ´óƼ1987 2026-08-20 16/800 2026-08-24 10:23 by ̫ɵÁË
[»ù½ðÉêÇë] ·Å°ñǰµÄ²»µ­¶¨ 20+4 snowwithsea 2026-08-19 17/850 2026-08-24 10:20 by echo8914667
[»ù½ðÉêÇë] ¿ÆÑй¶ùÌ«ÄÑÁË +18 ÎÒ4´ó°×²Ë 2026-08-20 19/950 2026-08-24 09:47 by ¿­¶÷¹ãÊ¢´ß»¯·ÖÎ
[»ù½ðÉêÇë] 93BebMhtakhǰºó11λ¿ªÍ·¶¼ÊÇ´óд +7 ÇÒÌý»¢Ð¥ 2026-08-17 8/400 2026-08-22 21:55 by ҽѧÀÏÄк¢
[»ù½ðÉêÇë] filecode£¬4¸öjtjcÁË +13 ziyangfang 2026-08-19 16/800 2026-08-22 17:08 by WH3796
[»ù½ðÉêÇë] ÈËÆø²»ÐÐÁË +8 fansofjerry 2026-08-21 8/400 2026-08-22 16:30 by zyqchem
[»ù½ðÉêÇë] ʱ¼ä´Á½ñÌ죬20ºÅ±äÁË +5 archvillain 2026-08-20 5/250 2026-08-22 06:12 by hui_daxiao
[»ù½ðÉêÇë] ¿´À´½ñÌì²»»á·Å°ñÁË£¿ +8 chengyan1220 2026-08-21 11/550 2026-08-21 17:52 by dcqxinyang
[»ù½ðÉêÇë] Ó¦¸ÃÊÇÏÂÖÜÈý26ÈÕ¹«²¼Á˰ɣ¿ +4 ¹þ¹þ¸ò£¿ 2026-08-21 4/200 2026-08-21 10:58 by Vivilian
[ÂÛÎÄͶ¸å] Ͷ¸å×Éѯ +5 wwm09 2026-08-17 7/350 2026-08-21 10:11 by ÆÚ¿¯ÂÛÎİïÊÖ
[»ù½ðÉêÇë] ½ñÌì·Å°ñûϷÁ衃 +9 yuleib84 2026-08-19 11/550 2026-08-21 10:06 by gltch
[»ù½ðÉêÇë] »ù½ð°¡»ù½ð +4 longfie172 2026-08-20 4/200 2026-08-21 08:58 by mark mao
[»ù½ðÉêÇë] ÖØÒªÏûÏ¢£¬ÖÐÎçϵͳÔÚά»¤ +11 yuleib84 2026-08-18 12/600 2026-08-20 11:09 by xskun
[»ù½ðÉêÇë] Ã÷Ìì·Å°ñ£¿ +5 Shxjjxjkx 2026-08-18 5/250 2026-08-18 18:14 by -´ó´ó´ó´ó´ó-
ÐÅÏ¢Ìáʾ
ÇëÌî´¦ÀíÒâ¼û